Basics Of Artificial Intelligence | AI Basics For Beginners | AI Training For Beginners |Simplilearn

0:06 Hello everyone, welcome to this amazing video on artificial intelligence basics. Artificial intelligence or AI as it is popularly known is a broad term that refers to the development of intelligent agents that can perform task that typically require human intelligence such as visual perception, speech recognition, problem solving and decision making. These agents are not only able to perform these tasks, but they can also learn from experience and improve over time. From medical diagnosis to predicting the stock market and making trades from improving the accuracy of self-driving cars to creating realistic virtual assistants, better voice assistant, and intelligent robots, AI has the capability to greatly enhance our daily lives. Simply put, AI is the future. With the pace of technological change accelerating every year, it's becoming increasingly

0:52 important to have a deep understanding of AI and its application. As you continue to advance in AI research and development, there will be an increasing number of opportunities for professionals who possess this expertise. Whether you are a developer, a data analyst, or just someone who is curious about the future of technology, learning AI is an investment in your own future as well as in your future of your society as a whole. So let's dive in and start exploring the incredible world of artificial intelligence. And now we are thrilled to present our AI boot camp that is designed to equip you with the knowledge and skills you need to thrive in this fast-paced and ever evolving field. In this 6 months intensive and immersive learning experience, you'll have the opportunity to dive head first into the subject matter, gaining hands-on experience and building a

1:38 strong foundation in AI. We believe in a practical approach where you will work on 25 plus hands-on projects across various industry verticals providing you with real world experience. What sets our boot camp apart is our partnership with Kelt CDME ensuring academic excellence and industry recognition by successfully completing the boot camp. You will earn a prestigious certificate and up to 22 CU credits from Kel Ctm validating your expertise in the field. So are you ready to embark on this transformative journey? Are you ready to unlock the power of AI and take your career to new heights? If so, enroll in our AI boot camp today and become part of the AI revolution. The course link is mentioned in the description box below. But before we begin, let's check out what one of our learners has to say about our

2:27 courses. Artificial intelligence has already become a part of our lives and I wanted to learn more about it. The course is helping me tremendously in my upskilling journey. Hi, I'm Daniel Dick. I'm 66 years old and I'm semi-retired and live in California with my wife and son. Since childhood, I've had a strong interest in science and technology. I was fascinated by the way systems worked internally and how algorithms performed. But after 40 years of working in technology sector, I could no longer work. It hit me hard. I looked at how well my daughter was doing as a software engineer. My daughter became my inspiration to upskill and over the years I pursued various courses in

3:15 different fields of computer science. I realized the technology has the power to change the world. I worked rigorously in the healthc care sector as a technocrat and I know technology can revolutionize it. I wanted to know how it could be used in the healthc care sector and other sectors so I could contribute to those domains whenever I start something of my own. The course is practical. All the minute details and concepts are explained in the most simplistic manner. The curriculum was welldesigned considering learners from different backgrounds. It was an amalgamation of practical labs and theory. The program focuses on building a problem-solving

4:02 attitude in learners. The course is helping me tremendously in my upskilling journey and solving real life problems. Whatever the problem is, you can either solve it or learn to solve it by upskilling yourself. And now we'll have a look on agenda for our AI basics tutorial. Starting with what is artificial intelligence. Then we'll have a overview of AI road map for 2023. Then we'll have an explanation of different types of artificial intelligence. Then we'll showcase the top 10 AI applications. And after this we'll see the future of artificial intelligence. And after that we'll have exploration of machine learning starting with introduction to machine learning. Then overview of different types of machine learning. Then we'll have comparison of

4:48 supervised unsupervised and reinforcement learning. And after that we'll deep dive into linear regression analysis and its application in R. And then we'll have introduction to logistic regression and its implementation in Python. And then we have comparison of linear regression and logistic regression. And then we'll see machine learning techniques and tools starting with classification in machine learning. Then we'll explore decision tree in machine learning. And then we'll showcase the top 10 AI tools for 2023. And after that, we'll highlight the top 10 AI robots in 2023. And after that, we'll present exciting artificial intelligence project ideas for 2023. And after this, we'll have an introduction to the top 10 AI companies for 2023 and

5:36 the discussion on the career opportunities in artificial intelligence for 2023. It's a weekend and John decided to watch the latest movie recommended by Netflix at his friend's place. Before heading out, he asked Siri about the weather and realized it would rain. So, he decided to take his Tesla for the long journey and switched to autopilot on the highway. After coming home from the eventful day, he started wondering how technology has made his life easy. He did some research on the internet and found out that Netflix, Siri, and Tesla are all using AI. So, what is AI? AI or artificial intelligence is nothing but making computers based machines think and act like humans. Artificial intelligence is

6:21 not a new term. John McCarthy, a computer scientist, coined the term artificial intelligence back in 1956. But it took time to evolve as it demanded heavy computing power. Artificial intelligence is not confined to just movie recommendations and virtual assistants. Broadly classifying, there are three types of AI. Artificial narrow intelligence, also called weak AI, is the stage where machines can perform a specific task. Netflix, Siri, chatbots, spatial recommendation systems are all examples of artificial narrow intelligence. Next up, we have artificial general intelligence, referred to as an intelligent agent's capacity to comprehend or pick up any intellectual skill that a human can. We

7:07 are halfway into successfully implementing this space. IBM's Watson supercomputer and GPT3 fall under this category. And lastly, artificial super intelligence. It is the stage where machines surpass human intelligence. You might have seen this in movies and imagined how the world would be if machines occupy it. Fascinated by this, John did more research and found out that machine learning, deep learning, and natural language processing are all connected with artificial intelligence. Machine learning, a subset of AI, is the process of automating and enhancing how computers learn from their experiences without human help. Machine learning can be used in email spam detection, medical diagnosis, etc. Deep learning can be

7:52 considered a subset of machine learning. It is a field that is based on learning and improving on its own by examining computer algorithms. While machine learning uses simpler concepts, deep learning works with artificial neural networks which are designed to imitate the human brain. This technology can be applied in face recognition, speech recognition, and many more applications. Natural language processing, popularly known as NLP, can be defined as the ability of machines to learn human language and translate it. Chatbots fall under this category. Artificial intelligence is advancing in every crucial field like healthcare, education, robotics, banking, e-commerce, and the list goes on. Like in healthcare, AI is used to identify

8:38 diseases, helping health care service providers and their patients make better treatment and lifestyle decisions. Coming to the education sector, AI is helping teachers automate grading, organizing, and facilitating parent guardian conversations. In robotics, AI powered robots employ real-time updates to detect obstructions in their path and instantaneously design their routes. Artificial intelligence provides advanced data analytics that is transforming banking by reducing fraud and enhancing compliance. With this growing demand for AI, more and more industries are looking for AI engineers who can help them develop intelligent systems and offer them lucrative salaries going north of $120,000. The future of AI looks promising with

9:25 the AI market expected to reach $190 billion by 2025. Artificial intelligence is reshaping industries and transforming the way we live and work. It encompasses a wide range of technologies including machine learning, deep learning, natural language processing, computer vision and many more. With its ability to analyze vast amount of data and make intelligent decisions, AI has become a gamecher across various domains. Hi everyone, welcome to simply learns YouTube channel. This AI road map guides you in navigating the path towards building a successful career in artificial intelligence. The ultimate goal of artificial intelligence is to create intelligent missions that can perform complex task, exhibit humanlike intelligence and contribute positivity to society. AI presents exciting career

10:11 opportunity in various industries and sectors. roles like AI engineer, data scientist, NLP engineers, computer vision engineers, AI research scientist, robotic engineers and many more offer exciting prospects for working with cuttingedge technologies and making an impact through artificial intelligence innovation. According to glass door, the average reported salary of an AI engineer in the United States is around $15,000 per year. However, in India, it is 10 lakh peranom. Leading companies worldwide are fully aware of the immense value of AI and are actively pursuing skilled AI engineers to contribute to their research development and implementations of AI technology. Among this top companies are Google, Microsoft, Amazon, Goldman Sachs, Apple

10:56 and JP Morgan Chase. Therefore top companies hiring AI engineer provide excellent opportunity for aspiring professionals. On that note, elevate your career with our AI and ML course developed in partnership with PI University and IBM. Gain expertise in high demand skills such as machine learning, deep learning, NLP, computer vision, reinforcement learning, chat, GPT, generative AI, explanable AI and more. Unleash your potential and unlock exciting opportunity in the world of AI and ML. This course cover tools like Python, TensorFlow, KAS, Chad, JPT, OpenAI, Gym, Mattplot, LI and many more. So hurry up and find the course link in the description box for more details. Our learners have experienced huge success in their careers. Listen to their experience. Find the Simply Learn

11:43 course review link in the description box. Without any further delay, let's dive into the topic now. If you desire to become an AI engineer, here are the steps you can follow to achieve your goal. Firstly, obtain a strong foundation in mathematics and programming. Gain a strong foundation in creating mathematic concepts like linear algebra, calculus and probability theory. In addition to that, it is crucial to acure mastery of a programming languages like Python commonly used in AI and become proficient in coding. Then earn a degree in a relevant field. That means earn a bachelor's or master degree in computer science, data science, AI or a related field to gain a comprehensive understanding of AI principles and techniques. Next, gain knowledge in machine learning and deep learning. To become a AI engineer, develop

12:30 familiarity with ML algorithms, neural networks, and deep learning frameworks. Example, TensorFlow, PyTorch to train and optimize models using real world data set. Followed by that, work on practical projects. Gain hands-on experience and showcase your skills by working on AI projects. Moreover, build a portfolio of projects demonstrating your ability to solve AI problems, impressing potential employers. Then stay updated with the latest advancements. Stay updated with the latest trends and research in AI, a rapidly evolving field, and expanding your knowledge by reading research papers, participating in online courses and workshops, and joining AI communities. Next, collaborate and network. Engage with AI communities, attend conference, participate in online

13:15 forums to connect with professionals in this field. Collaborating with others can enhance your learning experience and open new opportunities. Later, seek internships or entry-level positions. Gain practical experience through AI internships or entry-level roles in industry or research institutions. This provides valuable exposures and help develop your skills. Finally, continuously learn and adapt in the rapidly evolving field of AI. Stay updated on new developments, explore specialized areas, and embrace emerging technologies and tools to pursue a career as an AI engineer. Now that we have covered the essential steps to become an AI engineer, let's explore the necessary programming languages and algorithms for aspiring AI engineers. So, mastering programming languages like

14:01 Python, R, Java, and C++ is vital for acquiring proficiency in AI. This languages enables you to construct and deploy models effectively. Additionally, it would help if you gain a thorough understanding of machine learning algorithms such as linear regressions, K nearest neighbors, n base and support vector missions. These languages and algorithms are fundamental tools in the field of AI. First, let's understand what really is artificial intelligence. Artificial intelligence is the science of building intelligent machines from vast volumes of data. This data can be structured, semistructured or unstructured in nature. AI systems learn from past experiences and perform humanlike tasks. Artificial intelligence enhances the

14:46 speed, precision, and effectiveness of human efforts. AI uses sophisticated algorithms and methods to build machines that can make decisions on their own. Deep learning and machine learning are the two subsets of artificial intelligence. So you need both machine learning algorithms and deep learning networks to build intelligent systems. AI is now being widely used in almost every sector of business such as transportation, healthcare, banking, retail, entertainment, and e-commerce. Now let's look at the different types of artificial intelligence. So AI can be classified based on capabilities and functionalities. Under capabilities, there are three types of artificial

15:32 intelligence. They are narrow AI, general AI and super AI. Under functionalities, we have four types of artificial intelligence. Reactive machine, limited memory, theory of mind, and self-awareness. Let's look at them one by one. First, we will look at the different types of artificial intelligence based on capabilities. So what is narrow AI? Narrow AI, also known as weak AI, focuses on one narrow task and cannot perform beyond its limitations. It aims at a single subset of cognitive abilities and advances in that spectrum. Applications of narrow AI are becoming increasingly common in our day-to-day lives as machine learning and deep learning methods continue to

16:18 evolve. Apple Siri is a simple example of an narrow AI that operates with a limited predefined range of functions. Siri often has challenges with tasks outside its range of abilities. IBM Watson supercomputer is another example of narrow AI which applies cognitive computing, machine learning, and natural language processing to process information and answer your questions. IBM Watson once outperformed human contestant Ken Jenkins to become the champion on the popular game show Jeopardy. Other examples of narrow AI include Google Translate, image recognition software, recommendation systems, spam filtering, and Google's page ranking algorithm. Next, we have general

17:03 artificial intelligence or general AI. General AI, also known as strong AI, has the ability to understand and learn any intellectual task that a human can. General artificial intelligence has received a $1 billion investment from Microsoft through open AI. It allows a machine to apply knowledge and skills in different contexts. AI researchers and scientists have not achieved strong AI so far. To succeed, they would need to find a way to make machines conscious, programming a full set of cognitive abilities. Fujitsu built the K computer which is one of the fastest computers in the world. It is one of the most notable attempts at achieving strong AI. It took 40 minutes to simulate a single second of neural activity. So it is difficult

17:50 to determine whether or not strong AI will be achieved in the near future. Tanhi 2 is a supercomput created by China's National University of Defense Technology. It currently holds the record for CPS at 33.86 paflops. Although it sounds exciting, the human brain is estimated to be capable of one exaflop. Now CPS means characters per second that a system can process. Third in the list of AI that is based on capabilities, we have super AI. Super AI exceeds human intelligence and can perform any task better than a human. The concept of artificial super intelligence sees AI evolved to be so akin to human emotions and experiences

18:36 that it doesn't just understand them. It evokes emotions, needs, beliefs, and desires of its own. Its existence is still hypothetical. Some of the key characteristics of super AI include the ability to think, solve puzzles, make judgments, and decisions on its own. Now, if you have enjoyed watching this video so far, please make sure to subscribe to our YouTube channel and hit the bell icon to stay updated with all the latest technologies. Also, if you have any questions related to this video, please put it in the chat section. Our team of experts will help you address your questions. Moving ahead now, we will see the different types of artificial intelligence based on functionalities.

19:22 In this category, first we have reactive machine. A reactive machine is the basic form of AI that does not store memories or use past experiences to determine future actions. It works only with present data. They simply perceive the world and react to it. Reactive machines are given certain tasks and don't have capabilities beyond those duties. IBM's Deep Blue, which defeated Chess Grandmaster Gary Caspro, is a reactive machine that sees the pieces on a chess board and reacts to them. It cannot refer to any of its prior experiences and cannot improve with practice. Deep Blue can identify the pieces on a chessboard and know how each moves. It can make predictions about what moves might be next for it and its opponent.

20:09 It can choose the most optimal moves from among the possibilities. Deep blue ignores everything before the present moment. All it does is look at the pieces on the chessboard as it stands right now and choose from possible next moves. Up next we have limited memory. Limited memory AI learns from past data to make decisions. The memory of such systems is short-lived. While they can use this data for a specific period of time, they cannot add it to a library of their experiences. This kind of technology is used for self-driving vehicles. They observe how other vehicles are moving around them in the present and as time passes. That ongoing collected data gets

20:55 added to the static data within the AI machine such as lane markers and traffic lights. They're included when the vehicle decides to change lanes to avoid cutting off another driver or being hit by a nearby vehicle. Mitsubishi Electric is a company that has been figuring out how to improve such technology for applications like self-driving cars. Then we have theory of mind. Theory of mind represents a very advanced class of technology and exists as a concept. This kind of AI requires a thorough understanding that the people and the things within an environment can alter feelings and behaviors. It should be able to understand people's emotions, sentiment and

21:42 thoughts. Even though a lot of improvements are there in this field, this kind of AI is not complete yet. One real world example of theory of mind AI is Kismmet, a robot head made in the late '90s by a Massachusetts Institute of Technology researcher. Kismmet can mimic human emotions and recognize them. Both abilities are key advancements in theory of mind AI. But Kismmet can't follow gazes or convey attention to humans. Sophia from Hansen Robotics is another example where the theory of mind AI was implemented. Cameras within Sophia's eyes combined with computer algorithms allow her to see. She can follow faces, sustain eye contact, and recognize individuals. She is able to process speech and have

22:28 conversations using natural language subsystem. Finally, we have self-awareness. Self-awareness AI only exists hypothetically. Such systems understand their internal traits, states, and conditions and perceive human emotions. These machines will be smarter than the human mind. This type of AI will not only be able to understand and evoke emotions in those it interacts with but also have emotions, needs and beliefs of its own. While we are probably far away from creating machines that are self-aware, we should focus our efforts towards understanding memory learning and the ability to base decisions on past experiences. So, let me ask you a question. Which are

23:16 the powerful AI assistants that you have come across? Please leave your answer in the comment section below and stay tuned to get the answer. So what are the top 10 applications of artificial intelligence? Social media. Today AI can create social media post for you. It can draft and target social ads. It can also automate monitoring and it has powers that most of what you see in any given social network. Facebook's picture recognition tools have been popular among users for a while, but the company is constantly working to make the algorithms better so

24:01 that users can browse photos without relying on tags or other nearby information. It will help to tag people in photos. Twitter understanding what tweets to recommend to users on their timelines is one of the numerous ways Twitter employs AI on its platform. It seeks to provide users with the most relevant tweets possible for an individualized experience. Twitter also uses AI to combat offensive statements. Instagram artificial intelligence is used by the platform to improve user experience, filter spam and increase the effectiveness of targeted

24:47 advertising. Users in the platform can search images of a specific activity, venue, event, restaurant, food and discovery experiences with the aid of tags and trending information. Automoils the automotive value chain which includes manufacturing, design, supply, production, post-p production, driving assistance and driver risk assessment systems is successfully implementing artificial intelligence. Tesla keeps an eye on the driver's eyes to detect signs of drowsiness and keep them from dozing off while operating a

25:35 vehicle. It is primarily used by the autopilot system to stop drivers from taking quick power naps while driving. Agriculture Forbes reports that global spending on smart agriculture, including artificial intelligence and machine learning, is projected to triple to $15.3 million by 2025. Precision agriculture, often known as artificial intelligence systems, is assisting in enhancing the overall quality and accuracy of harvest. Artificial intelligence technology aids in the detection of pest, plant diseases and under nutrition in farms. Artificial

26:21 intelligence sensors can identify and target plants before deciding which herbicide to use in the area. Artificial intelligence in gaming. The gaming industry is one another area where artificial intelligence technologies have gained popularity. Artificial intelligence can be utilized to develop intelligent humanlike non-person characters that can communicate with the players in order to improve game design and testing. It can also be used to forecast human behavior. The 2014 Alien Isolation video game employ artificial intelligence to follow the player around all the time. Two

27:08 artificial intelligence systems are used in the game. One is the director artificial intelligence who frequently knows where you are and the alien artificial intelligence which is controlled by sensors and behaviors and constantly chases the player. Next comes artificial intelligence in healthcare. Delays can be the difference between life and death in the healthcare industry. Artificial intelligence in healthcare has the potential to help providers in many areas of patient care and operational procedures enabling them to build on current solutions and solve problems quickly. covid-19 has eliminated the process of

27:54 developing vaccine. In order to create and test new medicines, drug manufacturers are increasingly turning to artificial intelligence solutions like deep learning. Because there are so many potential chemical combinations, creating new medications requires processing a lot of data. Artificial intelligence overcomes this difficulty by utilizing its exceptional performance with massive amounts of data. This capability results in a higher production of approved pharmaceuticals in a more rapid, less expensive and more effective research and development procedure. Robotics. Another area where artificial intelligence is frequently

28:41 applied is robotic. AI powered robots employ realtime updates to detect obstructions in their path and instantaneously design their roots. Robotics uses artificial intelligence to make machines more intelligent and capable of acting in variety of situations. Robots can also sense their environment or take in its views with the use of sensor. Similar to how humans have primary sensors, robotics uses a variety of sensing technology combined. There is a definite trend toward mobile autonomous robots that can intelligently gather, process, and manage data in

29:26 order to make the best decisions for manufacturing or production. AI in banking. The use of advanced data analytics by artificial intelligence will transform banking in the future by reducing fraud enhancing compilence. Anti-money laundering task that would typically take hours or days can now be completed in a matter of seconds thanks to artificial intelligence algorithms. Erica, a virtual assistant created by Bank of America is among the best instances of artificial intelligence chatbots in banking applications. This artificial intelligent chatbot can take

30:13 care of task like updating card security and reducing credit card debt. Daily life use of artificial intelligence. autonomous vehicle to teach computers to think and evolve like humans. When it comes to driving in any environment and object recognition to prevent accidents, companies like Toyota, Audi, Tesla use machine learning algorithms. Spam filters. The email that we regularly use features artificial intelligence that separates out junk emails and sends it to spam or trash folders, allowing us to see only the

31:00 filtered material. Gmail, a well-known email service, has achieved a filtration capacity of roughly 99.9%. Next comes facial recognition. Facial recognition algorithms are used by our favorite devices including phones, laptops, and personal computers to detect and identify users in order to grant safe access. Education sector artificial intelligence can assist educators with non-educational task such as facilitating and automating personalized messages to students, back office duties such as grading paperwork, organizing

31:48 and facilitating routine feedback, managing enrollment courses, etc. A student can receive additional learning resources or assistance with voice assistance even without the lecturer or teachers direct engagement. This lowers the expense of producing temporary handbooks and makes it simple to provide answer to frequently asked topics. Artificial intelligence is most commonly used in the field of e-commerce. During personalized shopping, recommendation engines are made possible by artificial intelligence technologies, allowing you to interact with your customers more effectively. Their browsing history,

32:34 preferences, and interest are taken into consideration while making these recommendations. It helps you build stronger bonds with your clients and increases brand loyalty. For instance, almost every page of Amazon's website offers personalized product recommendations. Credit card frauds, fake reviews are two most of the significant issues that e-commerce companies deal with. By considering the usage patterns, artificial intelligence can help reduce the possibility of credit card frauds taking place. Many customers prefer to buy a product or service based on customer reviews.

33:20 Artificial intelligence can identify and handle fake reviews. What is the answer to the question that I have asked about artificial intelligence assistant? They can be Google Assistant, Siri, Alexa, etc., moving on. In the area of artificial intelligence, significant advancement have been made and the results are clear. AI is a flexible tool that is applied across sectors to improve decision making, boost efficiency and get rid of repeated task. Researchers are preparing us for a revolution that will change the world forever by looking into the future of

34:06 artificial intelligence. This revolution isn't going to happen in a few decades, but in a few years, which means that the clock is ticking for now for businesses to start embracing AI. Artificial intelligence has become a part of our lives. Due to its revolutionary nature, artificial intelligence also faces numerous debates regarding potential impacts on individuals. Although it could be risky, it's also a fantastic opportunity. It is estimated that the global artificial intelligence market will reach $267 billion by 2027. People are worrying about losing their jobs as AI continues to advance because it has revolutionized industries across all sectors. But AI has increased the number

34:52 of jobs and possibilities available to individuals across all industries. Every machine needs a person to run it. Although AI has replaced certain occupations, it still creates more jobs for humans. AI can be categorized into three types. Firstly, weak AI performs specific tasks like Apple's Siri. General AI performs tasks like a human. The super AI is more capable than a human. But both general AI and super AI are hypothetical because these technologies are not yet developed and research is going on. However, the development of such AI will take a lot of time. The development of AGI will accelerate within the following 10 years. In fact, according to

35:40 researchers, there is a 25% probability that by 2023, AI will resemble humans when it comes to thinking capacity. Additionally, the current data boom, computer developments, and improvements in automated methods and machine algorithms will provide a solid foundation for platforms with human level AI. AI has occupied crucial sectors like healthcare, cyber security, e-commerce, agriculture, robotics, education, the military system, finance, gaming, and many more. AI is used in health care to identify diseases, helping health care service providers and their patients make better treatment and lifestyle decisions. We can say that

36:26 without AI, we couldn't have made the incredible recent advancements in fields like robotics, virtual reality, chat bots, face recognition, and autonomous vehicles. Smart robot advisers in finance, insurance, legal, media, and journalism will deliver instantaneous research or discoveries. In the upcoming years, it is anticipated that artificial intelligence and machine learning will become more prominent in the consumer market, which will immediately affect how well web development functions. Virtual assistants or chat bots will provide professional advice. Other advantages include strengthening governance through better decision-making processes, shortening time to market for R&D initiatives, and

37:11 streamlining transportation and supply chain networks. Given all these scenarios, AI is all set to revolutionize every sector in the near future. Given that it is expected to impact 60% of firms, artificial intelligence will continue to spread deeper into a wide range of industries in the upcoming years. It is currently driving development in our smart devices, cars, and favorite apps. In the coming years, AI will invade every aspect of our life and eventually surpass human intellectual capacity. It won't be long before artificial intelligence becomes a common part of our everyday lives. As it becomes more prevalent, it will allow us to live more efficiently and improve our lives by increasing their effectiveness,

37:57 efficiency, and concentration on the primary tasks that require people's attention. AI technologies are transforming many industry sectors. Artificial intelligence will change the world for the better. Sci-fi movies and books depict a future with sentinate machines capable of interacting with humans and performing tasks just like people would. What if we told you that this future is already a reality? All of this is already made possible by machine learning. Machine learning is the science of programming machines to think and act like humans without being specifically programmed to. We already use machine learning in our daily life without knowing it. Email spam recognition, spellch check, even the YouTube video recommendation which brought you here are implemented using machine learning. Machine learning uses

38:45 algorithms to learn tasks. These algorithms are fed with data from which they learn to perform these tasks. This means that over time as changes in data occur, we don't need to reprogram our application. Just let it find patterns and learn from the new data. Machine learning is a subset of artificial intelligence which is a science concerned with imparting human-like intelligence onto machines and creating machines which can sense, reason, act and adapt. Deep learning is a subbranch of machine learning which is inspired by the working of the human brain. Machine learning is leading us to a future where machines can learn and think and has opened us a whole new plethora of job opportunities. This was a brief intro to

39:30 machine learning. Let's talk about a life without machine learning. For someone who doesn't know anything about machine learning or artificial intelligence, he or she might think that it is only being used in robots or machines and stuff, which is actually true as portrayed by most of the sci-fi movies nowadays. But you wouldn't believe how much more machine learning is giving us, how much of it we are using in our daily lives. Let's say you need information on any random topic. say a computer, the first place you would check would definitely be Google, right? It would collect all the information on the word you search for and present it to you according to relevance. If there was no Google, you would have to do it in a very hard way. That is by going through tens or hundreds of books and articles even after which you won't find the answer.

40:18 If we go back four to 5 years, facial recognition would be a thing only showed in movies like Mission Impossible or Terminator or any of the sci-fi movies you pick. But machine learning has made it possible for Facebook and Instagram to use this feature for your benefits. You don't have to go through the trouble of tagging every single person present in a picture that you have posted. Facebook will automatically recognize the people in the photo and tag them for you. That saves a lot of time for you, doesn't it? Also, Siri, Kotana, Iris, all of them would not be there to help you if there was no machine learning. Now that we know life would be a lot more difficult without machine learning, let's look into the things that are run by machine learning and we are using

41:03 them on our daily basis. Let's enter the world of gaming. PS4s and Xboxes have introduced virtual reality glasses which brings a whole new level of detail into gaming. Every time your head moves in real world, it replicates the movement in the virtual world providing an excellent gaming experience. Then there is gesture control gaming where in machine learning tracks your body movement and makes a corresponding movement in the game. Finally, in the game FIFA, your opponent tends to adapt based on the kind of strategy or gameplay you follow. That is again done by machine learning. I'm sure you must have shopped a lot from Amazon. So let's look into some of the places Amazon makes use of machine learning. Let's say you buy a formal t-shirt on Amazon. Now as you buy

41:51 it, it suggests you formal shoes, ties, blazers, and apparel that go with what you have bought. That's the recommendation system powered by machine learning. Again, the price on every product that you see on Amazon is varying every moment based on demand. That's being done by machine learning algorithms. Then comes customer segmentation. Customer segmentation is one of the most crucial thing for all the e-commerce platforms. Machine learning helps them differentiate between customers based on what they buy, how frequent are they and their reviews. This helps the companies to make sure that their customers are taken care of and the needs are being fulfilled. Now let's talk about an app that you use on a daily basis to reach office on time. Yes, it's Uber caps.

42:39 Once you have traveled with Uber, you must have noticed that it suggests you the places you might want to go based on your previous journeys. When you're taking a share, how does the app make sure that the cab you get is traveled by the same route you want to travel in? There are so many factors like the distance, the traffic, the ratings, all of it is taken care of by machine learning. For the past 5 minutes, we have been talking about how machine learning is improving our lives, where all it is being used. I have probably said machine learning 100 times already. I think it's about time that I tell you what machine learning actually is. Let's take an ordinary system that you currently are using. It can't do much except from the basic operations that you already know about. Now let's add artificial intelligence or for a

43:26 layman's point of view, let's give the same machine the power to think on its own. That is what machine learning basically is. It's an application of artificial intelligence that provides systems the ability to learn on their own and improve from experience without being programmed externally. So if your computer had machine learning, it may be able to play the difficult parts of a game for you or probably solve a complicated mathematical equation for you. That could be really helpful. Let's dive in a little deeper and see how machine learning works. Let's say you provide a system with the input data that carries the photos of various kinds of fruits. Now you want the system to figure out what are the different fruits and group them accordingly. So what the system does it analyzes the input data. Then it tries to find patterns. Patterns

44:12 like shapes, size and color. Based on these patterns, the system will try to predict the different types of fruit and segregate them. Finally, it keeps track of all such decisions it took in the process to make sure it's learning. The next time you ask the same system to predict and segregate the different types of fruits, it won't have to go through the entire process again. That's how machine learning works. Now let's look into the types of machine learning. Machine learning is primarily of three types. First one is supervised machine learning. As the name suggests, you have to supervise your machine learning while you train it to work on its own. It requires labeled training data. Next up is unsupervised learning wherein there

44:58 will be training data but it won't be labeled. Finally, there's reinforcement learning wherein the system learns on its own. Let's talk about all these types in detail. Let's try to understand how supervised learning works. Look at the pictures very very carefully. The monitor depicts the model or the system that we are going to train. This is how the training is done. We provide a data set that contains pictures of a kind of a fruit, say an apple. Then we provide another data set which lets the model know that these pictures were that of a fruit called apple. This ends the training phase. Now what we will do is we provide a new set of data which only contains pictures of apple. Now here comes the fun part. The

45:44 system can actually tell you what fruit it is and it will remember this and apply this knowledge in future as well. That's how supervised learning works. You are training the model to do a certain kind of an operation on its own. This kind of a model is generally used into filtering spam mails from your email accounts as well. Yes, surprised, aren't you? So, let's move on to unsupervised learning. Now, let's say we have a data set which is cluttered. In this case, we have a collection of pictures of different fruits. We feed this data to the model and the model analyzes the data to figure out patterns in it. In the end, it categorizes the photos into three types as you can see in the image based on their similarities. So, you provide the data to the system and let the system do the rest of the work. Simple, isn't it? This

46:31 kind of a model is used by Flipkart to figure out the products that are well suited for you. Honestly speaking, this is my favorite type of machine learning out of all the three. And this type has been widely shown in most of the sci-fi movies lately. Let's find out how it works. Imagine a newborn baby. You put a burning candle in front of the baby. The baby does not know that if it touches the flame, its fingers might get burned. So, it does that anyway and gets hurt. The next time you put that candle in front of the baby, it will remember what happened the last time and would not repeat what it did. That's exactly how reinforcement learning works. We provide the machine with a data set wherein we ask it to identify a particular kind of a fruit. In this case, an apple. So what

47:18 it does as a response, it tells us that it's a mango. But as we all know, it's a completely wrong answer. So as a feedback, we tell the system that it's wrong. It's not a mango, it's an apple. What it does, it learns from the feedback and keeps that in mind. When the next time when we ask a same question, it gives us the right answer. It is able to tell us that it's actually an apple. That is a reinforced response. So that's how reinforcement learning works. It learns from his mistakes and experiences. This model is used in games like Prince of Persia or Assassin's Creed or FIFA wherein the level of difficulty increases as you get better with the games. Just to make it more clear for you, let's look at a comparison between supervised and unsupervised learning. Firstly, the data

48:04 involved in case of supervised learning is labeled. As we mentioned in the examples previously, we provide the system with a photo of an apple and let the system know that this is actually an apple. That is called label data. So, the system learns from the label data and makes future predictions. Now unsupervised learning does not require any kind of label data because its work is to look for patterns in the input data and organize it. The next point is that you get a feedback in case of supervised learning. That is once you get the output the system tends to remember that and uses it for the next operation. That does not happen for unsupervised learning. And the last point is that supervised learning is mostly used to predict data whereas

48:50 unsupervised learning is used to find out hidden patterns or structures in data. I think this would have made a lot of things clear for you regarding supervised and unsupervised learning. Now let's talk about a question that everyone needs to answer before building a machine learning model. What kind of a machine learning solution should we use? Yes, you should be very careful with selecting the right kind of solution for your model because if you don't, you might end up losing a lot of time, energy, and processing cost. I won't be naming the actual solutions because you guys aren't familiar with them yet. So, we will be looking at it based on supervised, unsupervised, and reinforcement learning. So, let's look into the factors that might help us select the right kind of machine learning solution. First factor is the

49:37 problem statement describes the kind of model you will be building or as the name suggests it tells you what the problem is. For example, let's say the problem is to predict the future stock market prices. So for anyone who is new to machine learning would have trouble figuring out the right solution. But with time and practice you will understand that for a problem statement like this solution based on supervised learning would work the best for obvious reasons. Then comes the size, quality and nature of the data. If the data is cluttered, you go for unsupervised. If the data is very large and categorical, we normally go for supervised learning solutions. Finally, we choose a solution based on their complexity. As for the problem statement wherein we predict the stock market

50:23 prices, it can also be solved by using reinforcement learning. But that would be very very difficult and timeconuming unlike supervised learning. Algorithms are not types of machine learning. In the most simplest language, they are methods of solving a particular problem. So the first kind of method is classification which falls under supervised learning. Classification is used when the output you are looking for is a yes or a no or in the form A or B or true or false. Like if a shopkeeper wants to predict if a particular customer will come back to his shop or not, he will use a classification algorithm. The algorithms that fall under classification are decision tree, knife base, random forest, logistic

51:10 regression and KNN. The next kind is regression. This kind of a method is used when the predicted data is numerical in nature. Like if the shopkeeper wants to predict the price of a product based on its demand, it would go for regression. The last method is clustering. Clustering is a kind of unsupervised learning. Again, it is used when the data needs to be organized. Most of the recommendation system used by Flipkart, Amazon, etc. make use of clustering. Another major application of it is in search engines. The search engines study your old search history to figure out your preferences and provide you the best search results. One of the algorithms that fall under clustering is K

51:57 means. Now that we know the various algorithms, let's look into four key algorithms that are used widely. We will understand them with very simple examples. The four algorithms that we will try to understand are K nearest neighbor, linear regression, decision tree and KN base. Let's start with our first machine learning solution. K nearest neighbor. K nearest neighbor is again a kind of a classification algorithm. As you can see on the screen, the similar data points form clusters. the blue one, the red one and the green one. There are three different clusters. Now, if we get a new and unknown data point, it disclassified

52:45 based on the cluster closest to it or the most similar to it. K in KN&N is the number of nearest neighboring data points we wish to compare the unknown data with. Let's make it clear with an example. Let's say we have three clusters in a cost to durability graph. First cluster is of footballs. The second one is of tennis balls and the third one is of basketballs. From the graph we can say that the cost of footballs is high and the durability is less. The cost of tennis balls is very less but the durability is high and the cost of basketballs is as high as the durability. Now let's say we have an unknown data point. We have a black spot

53:32 which can be one kind of the balls but we don't know what kind it is. So what we'll do we'll try to classify this using KNN. So if we take K is equal to 5, we draw a circle keeping the unknown data point in the center and we make sure that we have five balls inside that circle. In this case we have a football, a basketball and three tennis balls. Now since we have the highest number of tennis balls inside the circle, the classified ball would be a tennis ball. So that's how K nearest neighbor classification is done. Linear regression is again a type of supervised learning algorithm. This algorithm is used to establish linear relationship between variables, one of which would be

54:19 dependent and the other one would be independent. Like if we want to predict the weight of a person based on his height, weight would be the dependent variable and height would be independent. Let's have a look at it through an example. Let's say we have a graph here showing a relationship between height and weight of a person. Let's put the y-axis as age and the x-axis as weight. So the green dots are the various data points. These green dots are the data points and D is the mean squared error. That is the perpendicular distances from the line to the data points are the error

55:04 values. This error tells us how much the predicted values vary from the original value. Let's ignore this blue line for a while. So let's say if this is our regression line, you can see the distance from all the data points from this line is very high. So if we take this line as a regression line, the error in the prediction will be too high. So in this case the model will not be able to give us a good prediction. Let's say we draw another regression line here like this. Even in this case you can see that the perpendicular distance of the data points from the line is very high. So the error value

55:49 will still come as high as the last one. So this model will also not be able to give us a good prediction. So what to do? So finally we draw a line which is this blue line. So here we can see that the distance of the data points from the line is very less relative to the other two lines we drew. So the value of D for this line will be very less. So in this case if we take any value on the x-axis the corresponding value on the y-axis will be our prediction. And given the fact that the d is very low our prediction should be good also. This is how regression works. We draw a line a regression line that is in

56:36 such a way that the value of D is the least eventually giving us good predictions. This algorithm that is decision tree is a kind of an algorithm you can very strongly relate to. It uses a kind of a branching method to realize the problem and make decisions based on the conditions. Let's take this graph as an example. Imagine yourself sitting at home getting bored. You feel like going for a swim. What you do is you check if it's sunny outside. So that's your first condition. If the answer to that condition is yes, you go for a swim. If it's not sunny, then the next question you would ask yourself is if it's raining outside. So that's condition number two. If it's actually raining, you cancel the plan and stay indoors. If it's not raining, then you would

57:22 probably go outside and have a walk. So that's the final node. That's how decision tree algorithm works. You probably use this every day. It realizes a problem and then takes the decisions based on the answers to every conditions. Nightb algorithm is mostly used in cases where a prediction needs to be done on a very large data set. It makes use of conditional probability. Conditional probability is the probability of an event say A happening given that another event B has already happened. This algorithm is most commonly used in filtering spam mails in your email account. Let's say you receive a mail. The model goes through your old spam mail records. Then it uses space theorem to

58:07 predict if the present male is a spam mail or not. So P C of A is the probability of event C occurring when A has already occurred. P A of C is the probability of event A occurring when C has already occurred. and P C is the probability of event C occurring and PA is the probability of event A occurring. Let's try to understand KN base with a better example. Night base can be used to determine on which days to play cricket based on the probabilities of a day being rainy, windy or sunny. The model tells us if a match is possible. If we consider all the weather conditions to be event A for us and the probability of a match being

58:53 possible event C. So the model applies the probabilities of event A and C into the base theorem and predicts if a game of cricket is possible on a particular day or not. In this case, if the probability of C of A is more than 0.5, we can be able to play a game of cricket. If it's less than 0.5, we won't be able to do that. That's how NY's algorithm works. Let's look at the definition of each of these learning techniques. Supervised learning uses labeled data to train machine learning models. Label data means that the output is already known to you. The model just needs to map the inputs to the outputs. An example of supervised learning can be to train a machine that identifies the

59:39 image of an animal. Below you can see we have a trained model that identifies the picture of a cat. Unsupervised learning uses unlabelled data to train machines. Unlabelled data means there is no fixed output variable. The model learns from the data, discovers patterns and features in the data and returns the output. Here is an example of an unsupervised learning technique that uses the images of vehicles to classify if it's a bus or a truck. So the model learns by identifying the parts of a vehicle such as the length and width of the vehicle, the front and rear end covers, roof hoods, the types of wheels used, etc. Based on these features, the model classifies if the vehicle is a bus or a truck. Reinforcement learning trains a

1:00:24 machine to take suitable actions and maximize reward in a particular situation. It uses an agent and an environment to produce actions and rewards. The agent has a start and an end state, but there might be different parts for reaching the end state like a maze. In this learning technique, there is no predefined target variable. An example of reinforcement learning is to train a machine that can identify the shape of an object given a list of different objects such as square, triangle, rectangle or a circle. In the example shown, the model tries to predict the shape of the object which is a square here. Now let's look at the different machine learning algorithms that come under these learning techniques. Some of the commonly used supervised learning

1:01:10 algorithms are linear regression, logistic regression, support vector machines, K nearest neighbors, decision tree, random forest and knive base. Examples of unsupervised learning algorithms are K means clustering, hierarchical clustering, DB scan, principal component analysis and others. Choosing the right algorithm depends on the type of problem you're trying to solve. Some of the important reinforcement learning algorithms are Q-learning, Monte Carlo, SARSA and deep Q network. Now let's look at the approach in which these machine learning techniques work. So supervised learning takes labeled inputs and maps it to known outputs which means you already know the target variable. Unsupervised learning finds patterns and

1:01:56 understands the trends in the data to discover the output. So the model tries to label the data based on the features of the input data. While reinforcement learning follows trial and error method to get the desired solution. After accomplishing a task, the agent receives an award. An example could be to train a dog to catch the ball. If the dog learns to catch a ball, you give it a reward such as a biscuit. Now let's discuss the training process for each of these learning methods. So supervised learning methods need external supervision to train machine learning models and hence the name supervised. They need guidance and additional information to return the result. Unsupervised learning techniques do not need any supervision to train

1:02:43 models. They learn on their own and predict the output. Similarly, reinforcement learning methods do not need any supervision to train machine learning models. And with that, let's focus on the types of problems that can be solved using these three types of machine learning techniques. So, supervised learning is generally used for classification and regression problems. We'll see the examples in the next slide. And unsupervised learning is used for clustering and association problems. While reinforcement learning is reward- based. So for every task or for every step completed there will be a reward received by the agent and if the task is not achieved correctly there will be some penalty used. Now let's look at a few

1:03:29 applications of supervised unsupervised and reinforcement learning. As we saw earlier supervised learning are used to solve classification and regression problems. For example, you can predict the weather for a particular day based on humidity, precipitation, wind speed, and pressure values. You can use supervised learning algorithms to forecast sales for the next month or the next quarter for different products. Similarly, you can use it for stock price analysis or identifying if a cancer cell is malignant or benign. Now, talking about the applications of unsupervised learning, we have customer segmentation. So based on customer behavior, likes, dislikes and interests, you can segment and cluster similar customers into a group. Another example where unsupervised

1:04:14 learning algorithms are used is customer churn analysis. Now let's see what applications we have in reinforcement learning. So reinforcement learning algorithms are widely used in the gaming industries to build games. It is also used to train robots to perform human tasks. Profit estimation of a company. If I was going to invest in a company, I would like to know how much money I could expect to make. So, we'll take a look at a venture capitalist firm and try to understand which companies they should invest in. So, we'll take the idea that we need to decide the companies to invest in. We need to predict the profit the company makes and we're going to do it based on the company's expenses and even just a specific expense. In this case, we have our company, we have the different

1:05:00 expenses. So we have our R&D which is your research and development. We have our marketing. Uh we might have the location. We might have what kind of administration it's going through. Based on all this different information, we would like to calculate the profit. Now in actuality there's usually about 23 to 27 different markers that they look at if they're a heavy duty investor. We're only going to take a look at one basic one. We're going to come in and for simplicity, let's consider a single variable R&D and find out which companies to invest in based on that. So we take a R&D and we're plotting the profit based on the R&D expenditure, how much money they put into the research and development and then we look at the profit that goes with that. We can predict a line to estimate the profit. So we can draw a line right through the data. And when you look at that, you can

1:05:46 see how much they invest in the R&D is a good marker as to how much profit they're going to have. We can also note that companies spending more on R&D make good profit. So, let's invest in the ones that spend a higher rate in their R&D. What's in it for you? First, we'll have an introduction to machine learning, followed by machine learning algorithms. These will be specific to linear regression and where it fits into the larger model. Then, we'll take a look at applications of linear regression, understanding linear regression, and multiple linear regression. Finally, we'll roll up our sleeves and do a little programming in use case profit estimation of companies. Let's go ahead and jump in. Let's start with our introduction to machine learning along with some machine learning algorithms and where that fits in with linear regression. Let's look at

1:06:31 another example of machine learning. Based on the amount of rainfall, how much would be the crop yield? So, we here we have our crops, we have our rainfall, and we want to know how much we're going to get from our crops this year. So we're going to introduce two variables independent and dependent. The independent variable is a variable whose value does not change by the effect of other variables and is used to manipulate the dependent variable. It is often denoted as X. In our example, rainfall is the independent variable. This is a wonderful example because you can easily see that we can't control the rain, but the rain does control the crop. So we talk about the independent variable controlling the dependent variable. Let's define dependent

…