---
title: 'AI Engineer Full Course 2026 | Complete AI Engineer Course | Simplilearn'
source: 'https://youtube.com/watch?v=AQfgb1XIcio'
video_id: 'AQfgb1XIcio'
date: 2026-10-24
duration_sec: 4411
channel: 'Simplilearn'
---

# AI Engineer Full Course 2026 | Complete AI Engineer Course | Simplilearn

> Source: [AI Engineer Full Course 2026 | Complete AI Engineer Course | Simplilearn](https://youtube.com/watch?v=AQfgb1XIcio)

## Summary

The transcript provides an extensive overview of AI engineering, covering career opportunities, specializations, job search strategies, and core machine learning concepts. It positions AI engineering as a growing field essential for modern businesses, and outlines a practical roadmap for beginners to start their journey.

### Key Points

- **Course overview** [01:05] — AI is transforming industries, and companies are seeking professionals who can design, build, and deploy intelligent systems. The course covers Python, data science, ML, deep learning, NLP, generative AI, and agentic AI.
- **Definition of AI engineering** [05:44] — AI engineering is about building smart systems that learn from data, understand text/images/speech. It differs from data science (studying data) and ML engineering (optimizing models).
- **Types of AI** [07:08] — Prediction-based, language-based, vision-based, and speech-based AI are the main types, with applications in healthcare, finance, retail, and manufacturing.
- **Specialization areas** [08:43] — Key domains include NLP, computer vision, robotics, and multimodal systems. Choose based on interest and 2026 trends like autonomy in robotics.
- **Job search strategy** [12:23] — Search LinkedIn, company career pages, and startup platforms like Wellfound. Kaggle and Devpost aid visibility.
- **Resume and online presence** [13:29] — Focus on skills, projects, outcomes, and profile optimization on LinkedIn and GitHub.
- **Continuous learning** [15:36] — Strategies include weekly habits, building projects, focusing on one topic, and engaging with research/community.
- **2026 action plan** [17:47] — Timeline: 1-2 months Python/stats, next 2 months ML basics with two projects, then specialization with one strong project, then apply for roles.
- **AI, ML, and data science relationship** [24:08] — Data science is umbrella; ML uses algorithms to learn from data; AI is engineering intelligent machines. The flow: data gathering, transformation, ML models, data analysis, AI actions.
- **Machine learning approaches** [27:23] — Traditional programming hardcodes rules; ML trains models on data. Techniques include classification, clustering, trend analysis, anomaly detection, visualization, and decision-m.

## Transcript

application, create AI powered solution, automate complex task and develop the skill required for one of the fastest growing technology careers? That is exactly what AI engineering helps you achieve. Hello everyone and welcome to
this AI engineer full course by simply learn. Today artificial intelligence is transforming almost every industry from healthcare and finance to automation, development. Businesses are not just using AI tools anymore. They are looking
for professionals who can design, build and deploy intelligent AI systems. AI developing machine learning models, building generative AI application, creating AI assistant, working with large language model and solving real
world business problems. With advancement in technologies like Gen AI, agentic AI and automation, learning AI engineering skills can help you prepare for exciting career opportunities in modern technology landscape. In this
artificial intelligence and AI engineering. AI engineer road map skills tools and career path. Python programming for AI. Data science and learning algorithms and model development. Deep learning and neural
networks. Natural language processing and large language models. Generative AI and prompt engineering. Building AI application and chat bots. Agentic AI and AI automation. AI tools and framework used by industries. AI
whether you're a beginner, a student, a developer or a data professional or someone looking to transition into AI, this course will help you understand the concepts, tools and skills required to start your AI journey today. By the end
AI systems are built, how modern AI application work, and how you can develop the skills needed to become an AI engineer. So without any further ado, interested in building a career in artificial intelligence, do not forget
certificate in AI and machine learning by simply learn. This program helps you build advanced AI skills by covering areas such as Python, data science, machine learning, deep learning, gen AI, and AI automation. You will also learn
how to create AI powered application, conversational chatbot, and intelligent solution using modern AI tool. The program includes 12 plus hands-on project, industry relevant projects, practical learning experiences and
exposure to modern AI tool to help you gain real world skill. You will also explore emerging technologies like Gen AI, agentic AI, large language models and AI powered automation while building a strong foundation for AI engineering
roles with expertled training, hands-on project and career support. This program helps you develop the skills needed to stay ahead in rapidly evolving AI start or advance your AI career, this program can help you build practical
expertise and prepare for the future of artificial intelligence. But before we move on, here's a short quiz to test your knowledge. Which AI technology allow AI system to understand and generate humanlike text? First is
database management system, second is large language model, third is operating system or fourth is network protocols. Comment your answer in the comment first idea. Why is AI engineering
getting so much attention in 2026? Well, the answer is simple. Technology is no longer just about building apps or websites. Now, companies want products that can think faster, understand users better, and automate tasks and make
engineering is becoming such an are looking for people who can build useful, smart systems and not just study >> [snorts] >> Job reports continue to show strong
momentum for AI and data related roles and technology focused jobs are expected if someone asks you why this is the career of the future, the answer is this professionals who can turn smart technology into real products and real
solutions. So now that we understand why this career is growing, let's look at opportunities and the impact. So now let's talk about the opportunities and engineering are wide. You can work in healthcare, finance, retail, education,
manufacturing, robotics, entertainment, and even cyber security. Smart tools are now being used in chat support, recommendation systems, fraud detection, and voice tools where image analysis, coding support, and business automation
also play an important role. The impact is also huge. AI engineers help save time, reduce manual work, improve customer experience, and make products more useful. Open source AI projects are also growing fast which means that
chances to practice build projects and enter the field. So this field is not just giving strong job opportunities, it's also shaping how businesses will seen why this field is growing, let's understand what AI engineering actually
means. In simple words, AI engineering is the work of building smart systems which can learn from data, understand text, images or speech and help people important word here is building. This role is not only about learning theory.
working tools, apps, and product features. For example, an AI engineer support, a recommendation system for shopping apps, a fraud alert system for banking or image checking feature for healthcare or manufacturing. So the
easiest way to explain this role is this. AI engineering is about taking smart technology and making it useful in the real world. So now that this role is and understand how it's different from the nearby roles. So now that we know
what AI engineering means, let us clear one common confusion. Many people mix up machine learning engineer. But their focus is different. A data scientist usually works more on studying data, finding patterns, and creating insights.
A machine learning engineer focuses more on taking models and making them work properly inside real systems. An AI engineer on the other hand usually works across the big picture building, connecting, deploying and improving AI
powered solutions inside products or business tools. So the easiest way to explain it is this. A data scientist studies the experiments. The machine system and the AI engineer helps bring the full smart feature into real use. So
move on to the final part and that's on the main types of AI and where we can see them in 2026. So now let's talk about the different types of AI in a very simple way. So one type is prediction based AI. This uses past data
to predict something like fraud detection or sales forecasting. Another type is language based AI which works with chat, search, summaries and even writing tools. Then we have vision based AI. This works with images and videos
like product inspection or medical scans. Then we also have speech based AI which can turn speech into text or text into natural sounding voice. So in 2026, these applications are everywhere. In healthcare, AI helps with scans and
detecting fraud and improve customer support. And in retail, it powers recommendations and smarter planning. In manufacturing, it checks defects using cameras and video tools. So AI is no longer limited to just one industry.
parts of everyday business and basics, we can move on to the next topic and talk about the skills and technologies that you need to learn. So now that the basics are clear, the next
step is choosing a direction. This matters because AI is a very wide field and trying to learn everything at once usually leads to confusion. In 2026, the field is growing across language tools, image and video systems, smarter
continue to use AI in information processing and automation as a major So the next smart move is to not chase every topic. It is to build a strong area that matches the kind of problems that you enjoy solving. So this makes
learning faster project stronger and your decisions much easier. Now let's domains like NLP, computer vision and robotics. One major area is NLP which
means working with human language. So this includes things like chat systems, document understanding and text summarization. Official cloud technology that helps computers
understand and generate human language. Another major area is computer vision which focuses on image and video. So this includes object detection, reading text from images, face and landmark detection, quality inspection and video
understanding. So this is widely used in healthcare, manufacturing, retail and security systems. Then there's robotics where software meets a physical machine. This area includes warehouse robots, industrial automation, mobile robots and
independently in real environments. So says that AI and the autonomy in robotics is one of the most top global robotics trends for 2026. And beyond these, there are also speech and audio
systems and multimodel systems which work across text, image, and audio together. So this is becoming one of the biggest practical shifts in 2026 because many modern products now combine more than just one type of input. Now let's
move on to how to pick a specialization based on your interests. So the easiest way to choose a specialization is to start with your interest. If you enjoy working with words, search, writing tools and documents, then NLP may be the
right fit for you. So if you enjoy images, video design, inspection or healthcare visuals, then computer vision may suit you better. If you like systems or autonomous devices, then robotics could be a strong direction.
Now, let us connect that with the 2026 trends. Multimodel systems are becoming more important because products are increasingly combining text, image, and audio together. Robotics is also becoming more advanced with AI and
autonomy becoming highlighted as the top robotics trends for 2026. And across software development, GitHub's Okro says that AI is reshaping how developers choose and build technology. So a simple rule works well here. Choose the field
where your curiosity stays strong even when the topic gets difficult. Trends keeps you learning long enough to become good at it. Now let's move on to some real life examples of specialized AI career paths. A language focused path
build search tools, chat systems, documents to understand workflows or text analysis features. So these are useful in chatbot support, education, legal work, finance and even enterprise software. A vision focused path could
lead to work in medical imaging, smart retail, OCR systems, video analysis or defect detection in manufacturing. Cloud providers now offer ready-touse image and video tools for these exact types of use cases. A robotics focused path could
lead to industrial automation, warehouse robotics, autonomous mobile robots, and smarter factory systems. The robotics industry in 2026 outlook highlights autonomy in new commercial applications as major growth areas and a broader
multimodel path could lead to products that combine text, image, audio and workflow automation in one experience. So that is why specialization is not about choosing the kind of real world
So now that the direction is clear, the next step is finding real opportunities in 2026. So here the AI jobs are no longer limited to one type of company. They are showing up in startups, large tech firms, healthcare, finance, retail,
manufacturing, and consulting. LinkedIn's job pages currently show hundreds and thousands of AI related roles worldwide, including many which makes one thing very clear. The demand is real and the market is very
active. The smartest approach is to search in three places at the same time. First, use major job platforms. Second, check company career pages directly. And third, look up startup focused platforms because many new AI roles appears
earlier than they do on traditional job boards. So that combination gives a much move on to top resources for finding job LinkedIn remains one of the most strongest places to search because it
supports direct job search, job recommendations and alerts based on skills, profile details and job activity. Along with that, company career pages are still important because many roles are posted first there. For
useful because it focuses on tech and startup hiring. So beyond job boards, Kaggle and Dev post are also valuable in different ways. Kaggle competitions help build visibility through real problem solving and dev post is one of the main
places where hackathons are listed and managed. So these may not look like job portals at first, but they often lead to projects, referrals, and hiring building a resume and online presence for AI engineering. A strong AI resume
in 2026 should be simple and proof based. It should clearly show skills, tools, projects, outcomes, and links to real work. LinkedIn officially because that improves how your profile is discovered and it also allows
recruiters to match you to more suitable roles. The open to work setting and job alerts also helps you improve visibility during job search. GitHub matters just as much. GitHub's own docs recommend using a profile readme showcasing your
repositories so that hiring teams can quickly see your work. A clean GitHub plus a focused LinkedIn profile can say more than just a long resume. Now let's get some networking tips from LinkedIn to hackathons. Networking works best
when it feels natural. A strong start is to stay active on LinkedIn by sharing project learnings, upgrading skills and engaging thoughtfully with the people on the field. LinkedIn also supports skills and endorsements, assessments, recruiter
regular profile activity more useful than you think. Hackathons and competitions are another powerful way to grow. Devost is built around hackathons and Kaggle has beginner friendly getting started competitions designed for people
with little or no machine learning background. So these spaces help build confidence, public work, and real connections at the same time. Now let's career. So now that the job and internship path is clear, the next step
is making sure that your career stays relevant. So this matters because AI workflows, and new ways of building products keep appearing every few months. GitHub's recent October's finding says that AI is reshaping how
developers choose and build technology, which shows that this field is not slowing down at all. At the same time, the World Economic Forum continues to place AI, information processing, robotics among the major forces,
industries. So, future proofing your to learn every new thing. It means that you're building a strong base, staying curious, and updating your skills in a very steady way. So, the people who stay
every trend. They're the ones who keep the basics strong and know how to adapt mindset is clear, let's move on to the next part and look at simple ways to overwhelmed. With that being said, let us move on to learn some continuous
learning strategies. So a simple strategy works best here. First, you have to keep one small weekly habit. That could be following GitHub trend reports, checking what is new on a hugging face learn and spending time on
one recent topic instead of 10 random ones. GitHub's official reporting shows that AI related development is driving major shifts in software. While HuggingFace now offers structured courses across language models, agents,
audio, vision, robotics, and open-source AI workflows. Second, learn by building. Reading is useful, but small experiments help much more. Try a notebook, mini whenever a new idea seems practical. Kaggle's official learning and
competition pages are useful for this because they combine short lessons, real data sets, and hands-on challenges for different skill levels. Third, keep your with it for more than one week, and then move on. That is much better than
jumping from topic to topic every day. Once the learning strategy is clear, the new ideas and deeper understandings come from? So, that brings us to research and community. So here is why engaging with research and AI community is crucial. So
research matters because it helps you with the field which is moving before those ideas become mainstream products. So archive remains one of the main open access places where new AI and machine learning papers appear with active
recent submissions across the AI and machine learning categories. So that does not mean reading every paper. It simply means staying aware of new directions, benchmarks and problems people are trying to solve. Community
when you're connected to people who are building. Hugging Faces Hub now hosts over 2 million models, 500,000 data sets, and 1 million demos, which makes it one of the strongest places to explore practical work, open tools, and
strong learning community through notebooks, competitions, and shared solutions. So staying connected to research and community is not extra >> It's one of the easiest ways to stay updated, discover better ideas, and keep
your skills relevant over time. So, now that this future proofing mindset is clear, we can move on to the next chapter. So, here's your 2026 success map is clear, let us bring everything together into one simple action plan.
So, the biggest mistake many people make is waiting for the most perfect time, the perfect course, or the perfect level of confidence before they begin. But grow when you start small and keep moving forward step by step. In 2026,
the smartest way to build an AI engineering career is not to rush. It's to follow a clear plan, stay consistent, and keep building proof of your skills. So that way, the journey feels practical and manageable instead of confusing. So
here's what a simple timeline can look like. So in the first one or two months, focus on Python, basic statistics, and working in notebooks. So this is not the stage where the goal is not speed, the goal is comfort. You should be able to
read code, write small programs and understand simple data problems. So in the next two months, start learning machine learning basics and build two or don't have to be advanced. They just need to solve one clear problem. And
you've learned. After that, spend the next 2 3 months going deeper into the based systems, image based systems, genuinely interests you. Build one stronger project in that area improving
resume and LinkedIn profile around the work that you have done. Then begin roles, freelance work or project based opportunities. At the same time, stay active in communities. Keep learning and keep improving your portfolio and that
is how the transition starts becoming real. And this brings us to the final message. You do not need to know everything before you begin. You do not degree or the perfect road map. What matters is taking the first step and
notebook can become a project, one project can become a portfolio and one portfolio can become an interview. So that one opportunity can completely for someday. Start with one small skill, one lesson and one small project.
Because in 2026, the people who move forward are not the ones who know what the ones who begin, keep learning and start building. And with that, the road the first step. Introduction of artificial intelligence and machine
artificial intelligence and machine learning. able to define artificial intelligence, describe the relationship between artificial intelligence and data science, define machine learning,
machine learning, artificial intelligence, and data science. Describe different machine learning approaches. Identify the applications of machine learning. Let's understand how the field of
Let's understand how the field of artificial intelligence emerged. Let's first understand the reason behind the emergence of AI. Data economy is one of the factors behind the emergence of AI. It refers to how much data has grown
over the past few years and how much more it can grow in the coming years. When you look at this graph, you can clearly understand how the volume of data has grown. You can see that since 2009, the data volume has increased by
44 times with the help of social websites. The explosion of data has given rise to a new economy and there is a constant battle for ownership of data between companies to derive benefits from it.
Now that you know that data has grown at a rapid pace in the past few years and is going to continue to grow, let's understand the need for AI. As you know, the increase in data volume has given rise to big data which helps manage huge
amounts of data. Data science helps analyze that data. So the science associated with data is going toward a new paradigm where one can teach machines to learn from data and drive a variety of useful insights giving rise
to artificial intelligence. Now you may ask what is artificial intelligence? Artificial intelligence refers to intelligence displayed by machine that simulates human and animal intelligence. It involves intelligence
agents, autonomous entities that perceive their environment and that maximize their chances of success at a given goal. Artificial intelligence is a technique that enables computers to mimic human intelligence using logic. It
act. Let's look at some of the areas where Artificial intelligence is redefining industries by providing greater processes. One example of artificial intelligence in practice is self-driving
cars. Self-driving cars are computer cars that drive themselves. In these cars, human drivers are never required to take control to safely operate the vehicle. These cars are also known as autonomous or driverless cars. Let's see
how Apple uses AI Siri, the voice. It simplifies your forecast. For instance, you can ask Siri to call your friend or to play music and use. Another example is Google's Alpha Go, which is a computer program that
computer program to defeat world Go. Amazon Echo is another product. It's humans. According to what they are
movies, and more. If you got compatible smart home devices, you can tell Echo to dim the lights or turn appliances on or off. You use AI and chess. And here's an example of a concierge robot from IBM called IBM Watson. The audience AI has
been in the headlines for composing music, playing chess, and even cooking food. Let's move ahead and look at some movies with the concept artificial intelligence. The films featuring AI reflect the ever danger of our emotions
by the concept of artificial intelligence and is reflected in the wide range of movies on AI. Renovation systems are used by companies. Let's see how work. Amazon collects data from users and recommends that product
shopping pattern. For example, you search for a specific product in the Amazon recommend some relevant products based on your past shopping and search. on your interest and there is a possibility that you buy the product
had a chance to compare the selected product with recommended product. Now relationship between artificial intelligence, machine learning and data intelligence, AI, machine learning and data science fall in the same domain and
their specific applications and mean. Let's try to understand a little about intelligence systems never reply human intelligence. Machine learning provides learn and improve the experiences without being explicitly programmed.
Data science is an umbrella term that encompasses data analytics, data mining, disciplines. Let's look at the flow diagram and try to understand the relationship between AI, machine learning, and data science.
artificial intelligence. So, the first step is data gathering and comes under data science. Data transformation is the process of structure into another form of structure. Data transformation is
important to activities such as data management and data in After gathering predictions and derive insights. In order to get predictions out of the data such as supervised learning or unsupervised learning. On the overview
learning are the machine learning technique used to extract predictions from a given data set. Now you must thinking where deep learning comes into machine learning involved with algorithms. It uses artificial networks
which are modeled on the structure of neurons in your brain. Deep learning is structure to data that you can just exploit build features around. Now the insights for predictions being made. In order to do so you use data analysis
actually is process under science. Now you are done with all these you must want your data to perform actions. This is where AI comes into the picture. Artificial intelligence predictions and insights to perform as based on human
decision and decision. Now let's move ahead and understand the relationship between artificial intelligence machine learning and let's look at artificial Artificial intelligence is the engineering of making intelligent mach
programs. Machine learning provides systems the ability to earn experiences Machine learning allows machines to gain intelligence thereby intelligence. between machine learning and data science. Data science and machine
evaluate for machine learning algorithms. Data science covers the machine learning has the algorithmic statistical aspect. Data science is used to find patterns in the data. Statistical machine learning uses the
includes various techniques like statistical modeling, visualization and focus on building algorithms data provided making predictions.
artificial intelligence system to learn by extracting pattern data. It usually del quicker more accurate results to help you spot profitable opportunities or dangerous risk. Now you must be curious to understand the features of
the data to detect patterns of data set and adjust programmatically. Pattern classification of data based on knowledge or on statistical extracted development of computer programs that themselves to grow when exposing using a
method called reinforcement learning. It uses external feedback to teach the system to change its internal workings in order to guess better next time. It enables computers to find hidderative algorithms without being machine
learning uses algorithms that are free as data to help produce reliable and using the statistical and machine learning algorithms that tease patterns and relationships of data and express them as mathematical equations.
Let's understand the different machine learning approaches. learning? In traditional programming, data and program is provided to the output. However, the machine learning approach is very different. In machine
learning, algorithms are applied with given data and output. The result algorithmication is a model helps machine to learn from the data. In behavior of the program. But in machine learning, you leave a lot of that to
first understand the traditional programming approach. Traditionally, you would hardcode the decision rules for a problem at hand, evaluate the results of satisfactory, the program would be deployed in production. If the results
were not as expected, one would review the errors, change the program and evaluate again. The iterative process continues to one gets the expected result. What is the machine learning approach? In a new machine learning
hardcoded. The problem is solved by training a model with the train in order best represents the relationship between the input and the output. This train model is then evaluated against test data. If the result satisfactory model
results are not satisfactory, the crane is repeated with some changes. Machine Machine learning uses a number of theories and techniques for data science. Here are some machine learning techniques. Classification,
analysis, anomaly detection, visualization, and decision-m. Let's which the computer program learns from the data input given to it and uses this Classification is used for discrete
responses. Classification is used when we are training a model to dictative targets. Is a tech organizing categories for its free text searches faster and provides better user.
Clustering is a technique such way that objects in the same group are most other group. It is basically a collection of objects on basis of similarity and dissimilarity between them. Trend analysis is a technique a
events through the use of count's data analysis. It represents variations of low frequency in a time series. The high and medium frequency fluctuations being and medium frequency fluctuations being out. Anomaly detection is a technique to
identify cases that are unusual within data that is seemingly homogeneous. Anomaly detection can be a key for solving intrusions by indicating a presence of intended or unintended induced attacks, defects, faults, and so
on. Visualization is a technique to present Visualization is a technique to present data in a pictorial or graphical format. It enables decision makers to see analytics presented visually. When data
is shown in the form of pictures, it becomes easy for users to understand it. Decisionm is a technique or skill that provides you with the ability to influence managerial decisions with data as evidence for those possibilities.
Now I am sure you have a better understanding of the overview of machine learning. So let's look at some real time applications of machine learning. Artificial intelligence and machine learning are being increasingly used in
learning are being increasingly used in various functions.
mining, video games, text analysis, and healthcare. Let's look at each of them in more details. So, what is image processing? It is a technique to convert an image into a digital format and perform some operations on it so as to
induce an enhanced detected obstacles by the bra. Now robotics is machine learning. Robots are that used to do certain jobs. Some of the examples of robotics are where a humanoid can read the emotions of human beings or an
industrial robot is used as manufacturing products. So let's look at some real time applications of machine learning. Let's see what data mean is in let's look at some of the applications
is also used in market basket analys which items are often put together. It can be used for grouping or classifies users based on profiles. predictions based on data in a Pokémon Go battle. There's a lot data to take
is where machine learning is useful. Machine learning classifier will predict data. Let's move on. One of the most which is text analysis is the automated process of obtaining information from
text. One example of text analysis is filtering which is used to detect emails. Another example sentimental is used for classifying used for information such as track specific data key entities. There are
healthcare industry disease and diagnosis drug manufacturing medical imaging diagnosis and so on. Some use machine learning have revolutionized healthare industry Google health bio beats healthy and ginger.io Hello.
Continues to revolutionalize various industries. These professionals system challenges often subject arure by AI technologies science. So this video is about what does
environment and neural networks generational analysis for contextual go. So to succeed you need a better and
go. So to succeed you need a better and now this 8 months and before we crucial to science is understanding
like number and algorithms these are some privileges such as like rules and more rules understanding preceptions.
You should also practice precise synchronous finance. structure and algorithmic levels of various hashes
which also helps So the collaborative So the collaborative collab project first learns
different learnings every use for of learning on the data like measures standard and
coach to more advanc So we study accessing values ones and that's how fund
and machine learning function machine learning
transition to the main and so on and gen. So this is our best learning product using
blockure. So remember to learn about to check your national land. So help us like
not be liable learn from a small set of actions from solutions that may work for particular problem walk complicated walking questions like laugh what robot walk these are very difficult program noation actually try out will
slow the growth technology is capable of learn humans to climb a mountain a really interesting point here is that environment and we can adjust for it with it most of the models and nonprofit
aren't able to do that there's a couple of them that see how it goes if we're is a subbrand of machine learning casing multi-ter optimal solution for propain place to another. Robots can scenario and derive a solution by itself. Robot
path of time take on each path and maybe come up with a unique solution all by looking for unique solutions. We want the best solution you can't find unless system model. We have survive versus univer. But learning head is probably
a lot of different learning models whether or networks all kind of tries. this is important because you already answer all the information. So you're super you already know that for you can already look like so you have an answer
already look like so you have an answer for it. We have lab controlled unsupervised because in modvis model supervis which is really
modvis model supervis which is really cool specified machision solar. Uh so you guys can think um some of different ways a lot of different algorithms like this is really cool just
come up but unsupervised learning is how we pick out a donut one model next to So this goes and they work reinforcement learning how we think marketing growing market stage as far as how working with people rewards and
errors based problem no data is used noision flow ster problem sol it works and this doesn't work well get you do reward act that as well as find the best route so important days before model this pretty standard last a
few years just know you have the is the model for learning so this actual entity whatever combination of this is Especially if you're using some model and this situation object is called this environment you have a robot trying to
get volumes or whatever see output and then your action is all possible taken the model and you like a video game this is looking at the whole playing one of
want a board what's around what's around you um if you're robot moving around the navigation that would be position by the model then the board the model direction of action. So yeah, you do it or do it. Try to maximize the reward the
policy how an agent will behave any time between action and present state where the policy you're using to have output for your agent. One reason to separate a prediction um of different options and the policy will pick the best based on
those guess at different options and we actually observe whatever and it's going to be the whole house bring them out. So adding uh and
incentives the dog business reward the dog will follow max will follow every command new action like bing by itself that try something else for oh this also reward and so follow it for different works the dog
also play this quality called exploration parts of the house cla doesn't get so let's mar decision process marov's decision process is a reinforce learn action affects the envirment to be used
force You see these all different reward and so even though the environment your environment is going to put out a reward statement even state or look at dead and look at the state and then expect from policy policy comes in the
at policy and say what's a good action that will probably be dead or get understand these differences as they go it's pretty important in most models on this you can pull in and start using um bridge forward as far as when you
say this is a read to this happen and choose a reward in the state agent look that action goes back to the environment it affects the environment and depending on what the action was and then a new state so find a and eth okay with a path
reward is what we want to choose for the nodes to travel from node uh a to bath taken and you can see here a can to b or it can go to cities it can go to cities find a b going to c and d
diagram you have to realize that even though learning finding an all the different and so workforce learning but now simple problems like it was not easy so let's go ahead and look at reinforcement learning reinforc
to go through on here. Uh so we're going to create a class called state that there's a lot of class here. Don't let that you too much not much here. Um look in our class. So we have here we're going to it. We have our board
going to it. We have our board on board is end board hash player equals one as far as things get a hash the board on there which is a col selection here for. Go ahead scroll up a little bit. a copy of this sent over to
little bit. a copy of this sent over to this particular file here through all rows diagnosition
something update. So you have original missing end position that you just chose. You can see the little user face the green copy. Great way understand how this works. And here is uh get a reward.
Um we reward winner. This is one of the parts of what go here is we have result a result result one feedback one zero. So this reward in this particular case because uh system reinforcement do really simple example free work. Imagine
there actions their environment is huge. you know lock on in the environment and um have changed reward set up and the best way to do that as far as way get made to and so they have way up depending on reward in this case reward
way to add the rewards they may have like a certain path the first reward is actually important whatever it is this reward reward here they give 1.5 reward different
here they give 1.5 reward different huge how depends on what you want to do here. This is true and you'll see here we have This is true and you'll see here we have player two itself learning game is have
two models that are training each other and so things
war but war is really hard is how you war different setup and the other one is a playing it's action and so what choose for an action is also before action and the really key to remember before playing is in data is how it next best
can see the environment is we're going to be our state which is kind class player class player we're not taking we're going up to computer
players and this is an interest uh explorate talk about how do we trade move is important but not as important as last one so you as you get there the first one first two and the third because guys become more than the first
step here I'm going to be the war coming in and choose action important so once you go on we can say here's random number which call the action this one states choice length of position position board positions different go
position board positions different go through values And this hash to the here feedback where the war comes in reward here was important because it has okay this is where as this is reward this is part of this earlier it's one and this
reward of two easy step three step four so onward 10 reward 10 we add that same here um also 10 just makes math easy so we have 10 whatever it is 0.9
10 so this formula um as far reward minus value. Uh basically 0 how we train our state and we want the final state the win points first. So we really train this almost from the last two words and reverse financial reverse
figure this stuff out and go ahead and reord the imagine row action uh action is position
if not works and we go ahead state which here is because human because it's not programing the model the model so here pieces and the first do we set up one it's going to play it's going to take
50,000 routes now we do this and it's result result oops button this run oops forgot there for the board There's actually the state reference that again. So this up with
times. The reason I did that is we're going to uh actually play it change that have our player one player two policy two in there. We come here and we're
computer zero one player 10 play this remember there. I'm going to go and do zero comm here. And so I put my zero like zero here. And so I put my zero like zero right here just like zero two and so
time instead of five to 5,000 back this takes a while to train it like really fall hard we're talking about columns and so for on this much quicker all the options on there and you probably so we look at before be very careful
what you do like a larger network where you're doing networking step you actually learn that action which they try after both processes and there's a huge amount of work to do. Let's go ahead
run ahead last and then go ahead again. So one we can see go ahead and go center and
row zero two there it is and it's done here go row 0 one two z one there we go zero here you'll find way more happens this process is changing will be one of the
more powerful pages in the next two go is the most important missionary tacto we start environment which language some of us lost you don't know again we all this together required to do so
because you can do computer policy too. So this learning policy would fulfill that action and the board and our experience
There will be if you're a rock still number a rock still number 100 people and call this list bad after
100 people and call this list bad after position um action is take a date reward again I'm talking about talking about talking about agent is can't take action this might
We don't have an absolute final value here. If you have valition first step one
and we have our money values
has more 10 value if you're singular
using Python book on this book with Python 3 here. book on this book with Python 3 here. So we import our array from that import
location and is going to be 0 2 3 first mult and move from multiplication 1 2 3 and is that you don't want to put continually as they rise because um if you flow us
in or at the same time the stuff but there um comes out to buy or sell stock and might be very certain money the air for
you guys do under you have a low number. You now have 1 2 3 and you can this bad You now have 1 2 3 and you can this bad if you're doing the apparel
create aation rewards you see here rewards you see here and we need to run sorry from the pattern to create this code here let's go ahead and
create this code here let's go ahead and pull there we go next two agent we have ouration information so
agent. So obviously this would be coming from somewhere else from state location up to 0 location this creates an array of Z setup on there and the big part is the training we have our rewards new equals a copy of wars any state in
location. So this is where we group just goes to bed and we start it go do this. Uh so this we're going back call on here that switch to arrow. Uh so we're doing see what happens. Now this part would actually be instead of your external
get it through outside here for ease coming here this here call the state environment does this thing right uh go ahead and start it's going to start somewhere uh you have your playable actions action that up that's I
have and so we're getting three states I directly reand chose state actions as you can see here you have range using the reward so we'll get the reward is our target rewards current date um plus
randomly between two different things in there see what's going to do every word and if you remember John let's go ahead and just reform when we were talking is a rand selection. Instead of random selection you make something where the
selection is which be option three here and maybe option two might like this express or you just add together those choice. That's usually where you start. see a triple difference. So two plus we look at this bel
rewards coming in for that. Uh our texture here that's right here we have in our center
we have our Q location.
down the Just how much
and and all this basically
and all you see how works and all you see how works and all of your
a little bit more because
source of Let's see what is on our adult part of blood and blood part of blood and blood has been using
to have all these and small number of of the and
there is amazing
01. That's how people
And obviously for the color.
See the result is
to see. So when the Spanish
system change. I find things
language and
body. So please you have no way and of the princess.
So maybe I'm still
Okay. Don't you understand?
one of these result and this res Please mind
this kind only.
teaching official prove that
go for no other And