Webinar on the Theory of Algorithms at Innopolis University
Good day, Dear readers!
Last week’s series of our webinars successfully crossed its equator, and today we want to announce the upcoming webinar, and also publish transcripts of the records of our listeners ’questions and the answers of our lecturers to them.
So, on March 11, at 18:00 (Moscow time), our professor Manuel Mazzara will hold a webinar on the topic of Theory of Algorithms (Theory of Computation). Hurry to register for the webinar on the link .
')
We remind you that the collection of applications for our undergraduate program continues.
Artificial Intelligence webinar, lecturer - Samir Belhauari
Question 1:
Professor, have you heard about the Human Brain project, whose goal is to create a simulation model of the human brain?
Answer: Yes, the HBP project is carried out by the university where I worked before - École polytechnique fédérale de Lausanne (EPFL-Switzerland). This project is funded by the European Union. They build a computer model of a real brain and thus try to learn all its secrets.
Question 2:
What languages are used in AI programming today?
Answer: It depends on the specific branch of AI (computer vision, machine learning, search, planning, robotics, natural language processing, etc.). I would say that you should choose the language that allows you to easily create prototypes of certain elements, for example, MATLAB. However, if you plan to build a system, then C or C ++ will be the best choice.
Question 3:
Could you give an example of how AI can be used in the oil and gas industry?
Answer: Today, artificial intelligence technologies are widely used in the modern oil industry, including oil and gas field simulations, optimization of drilling and production, drilling automation and process control in general.
Question 4:
What are the basic knowledge you need to have for successful learning in this subject?
Answer: You will need basic programming knowledge, Probability Theory, and Linear Algebra.
Question 5:
Does Markov Chain refer to dynamic programming?
Answer: Yes, it does. Markov chains are often used in solving problems of dynamic optimization.
Question 6:
Please tell me how well you need to understand the economy in order to develop AI mechanisms in this industry?
Answer: You need to know exactly what the economist wants from your model in order to develop an efficiently operating model. From the point of view of knowledge, I believe that you only need to know basic economic terms and general concepts.
Question 7:
What approaches exist in the field of computer vision for applications without a priori information. What ideas exist in the field of motion detection?
Answer: 1) The clustering algorithm will be used if there is no a priori information; 2) Motion detection works based on the frame differentiation method, which compares how the intensity of pixels changes its position from frame to frame. There are two options for motion detection: a) the first method considers changing the pattern as a whole; b) the second method considers the movement of the averaged array.
Question 8:
What can you say about the R language? I heard that he is quite popular in the field of machine learning. Is there a workshop on a programming language in the course itself?
Answer: The R language is often used because it is free and easily accessible on the web. I prefer to use MATLAB (we can add several tasks on the R language, if they wish). The course on Artificial Intelligence will have 5 tasks, during which students will be able to use MATLAB or C ++ for coding
Question 9:
Which of these organizations - IEEE or ACM has more authority in the field of Computer Science?
Answer: Both of these organizations are very authoritative.
Full webinar entry:
Artificial Cognitive Systems Webinar, lecturer - David Vernon
Question 1: Renat Shaikhutdinov
How do you test complex behaviors? For example, a simple function can be tested using unit tests, and what to do in this case?
Answer: The main problem is that cognitive systems deal with circumstances that cannot be fully detailed at the design stage, that is, it is assumed that cognitive systems face changing, unpredictable and non-integrity information. Testing these types of systems is extremely difficult. Of course, you can subject individual components to unit testing, but system testing is much more difficult. Most people solve this problem by testing the system in real conditions, observing how it interacts with animate and inanimate objects when looking at possible scenarios. You can do this in the laboratory by simulating a natural environment (for example, a kitchen), or test it in a natural environment, setting a task for it, and observing its behavior when it tries to perform a specific task.
Question 2: Viktor Smirnov
Professor Vernon, in your presentation you conceptually share learning and development. How common is this division in cognitive science and / or robotics?
Answer: The difference between training and development lies in the fact that during the course of training, an adaptation (calibration) of the model provided by a third-party subject occurs, and during development the subject creates his own model. Thus, training is based on determining the parameters of a model provided by another subject, while development is based on the independent creation of a model. This division is not yet so common in the scientific community, but it has proven very useful in explaining the technical methods and processes underlying both problems. Of course, there are other ways to separate learning and development. For example, training is usually focused on one skill or knowledge, while development involves the acquisition of a multitude of skills and knowledge and an understanding of their relationships. Also, learning often involves understanding how the world functions, often without considering the agent’s view of the situation. Development is always connected with the attitude of the abilities of the subject in the context of how the world functions. In psychology, development is a process that a subject goes through with the goal of expanding its set of possible actions and extending its time span for its prospecting ability (that is, its ability to anticipate events and the need to act).
Question 3: Anatoly Sviridenkov
Do you use any particular logic for knowledge? If so, what type? First order logic?
Answer: Most cognitive systems, such as Soar and ACT-R, use a production model, that is, they are rule-based systems with conditions and related actions. Although they do not use formal logic, they are, in essence, the application of first-order predicate calculus, that is, first-order logic. Emergent (from the English. Emergent - arising, unexpectedly appearing) cognitive systems do not denote knowledge using symbols and therefore do not use formal logic to justify or denote knowledge. Instead, they use commutative methods and associative techniques to present and operate information.
Question 4: Dmitry Chesnakov
In your presentation, are you talking about MOOC (mass open distance courses) or about the course at Innopolis University?
Answer: This is a course at Innopolis University. Professor Vernon will give the course “Artificial Cognitive Systems” in the second semester of the 2014-2015 school year.
Question 5: Viktor Smirnov
How important is the problem of modeling phenomenal consciousness in modern cognitive systems?
Answer: Opinions diverge. Some scientists believe that there is no need to use the concept of consciousness in the study of the process of knowledge. Others are convinced that this is an integral part of knowledge. What is exactly true is that the study of computational models of consciousness at the moment is a recognized area of study and the study of the process of cognition plays an important role. In my course, we will not address much of the topic of consciousness, only when studying various types of memory (procedural and declarative memory)
Question 6: Anatoly Sviridenkov
What do you think about deep learning in cognitive systems? Is it possible to combine character and sub-character levels?
Answer: Great question! Most of the scientific community believes that this is important. When I talked about cognitive architectures, I mentioned a cognitive and emergent approach. The combination of these two approaches is called hybrid cognitive architecture. There are many well-known hybrid cognitive architectures, such as CLARION and ACT-R. The basic idea is precisely what you propose: to combine symbolic and sub-symbolic forms of knowledge, that is, knowledge that is explicit and is represented by a symbolic system and knowledge that is implicit and is often represented using commutative techniques such as artificial neural networks.
Question 7: Anatoly Sviridenkov
In which area do you expect a breakthrough: brain modeling, machine learning, or artificial intelligence?
Answer: I think in the field of machine learning, but all three areas are very important. For example, a lot of research is currently being done on brain modeling. The results have already had an impact on several computing systems, such as the mirror neural system. Personally, I expect several key breakthroughs in the study of autonomous systems.
Question 8:
In your presentation, you pay great attention to various types of memory. Why does the machine have so many types of memory?
Answer: We need different types of memory to encode different types of knowledge. For example, there is declarative knowledge that relates to facts about the world (metals are hard, boiling water is very hot, etc.). Another type of knowledge is knowledge based on skills, the ability to do things. This is procedural knowledge. They are encoded in a separate type of memory and require different views when you create an artificial system. We call it procedural memory. There is also a short-term and long-term memory, the short-term memory stores knowledge only as long as it is necessary to perform a task, the long-term memory contains all the experience of the subject.
Full webinar entry:
Webinar Component-Based Software Engineering, lecturer - Manuel Mazzara
Question 1:
Today, companies and people operate with huge amounts of data. Companies at the same time accumulate the entire history of transactions, management information and other data. People save a lot of media data. But in real life there are no organisms capable of storing all sensory information. Is there a paradigm in the field of software development that deals with this issue?
Answer: As far as I know, such a paradigm does not exist now. This area is very new now. Big Data, Data Mining and to a certain extent Deep Web are areas that are related to the problem you mentioned.
Question 2:
Do you think computers and machines will surpass our abilities in the future if technology develops at such a pace? How can humankind prevent this, to always stay ahead.
Answer: My personal opinion is no. There are certain things that only a person can do; machines can never make them. The speed of technology development and the speed of machines have no relation to this. There are separate thought processes that machines simply cannot have. For example, computability and Turing-Church conjecture. Naturally, this is just my opinion. However, there is no evidence to the contrary. Some of my colleagues are confident that in 50 years we will have machines that are conscious. I'm not sure this will happen.
Question 3:
As far as I understand, we use component-based software engineering daily. Is there any difference between CBSE and traditional programming techniques?
Answer: The need for software decomposition into smaller components exists not only in the last 10 or 15 years, but much longer. At the very beginning of the development of computer science, it became obvious that big problems are more effectively solved if we divide them into small parts. CBSE is certainly part of Software Engineering. CBSE is an evolutionary development of previous concepts, such as structured programming and object-oriented development.
Question 4:
What areas of IT development are most important these days, and will be most important in the near future?
Today, cloud computing, Big Data and Data Mining are much discussed. With the advent of social networks, we have noticed a tremendous commercial interest in these areas (from Facebook, Twitter, etc.)
Answer: Another important aspect is the field of e-medicine, the technology in which is used to improve the quality of life of people, especially the elderly and with disabilities. We can help these people thanks to modern technology. For example, it can be implemented through mobile applications and devices. Personally, I plan to pay special attention to these areas in the future.
Question 5:
What do you think about really decentralized systems? For example, systems in which all links are interchangeable?
Answer: This question is very interesting. Such systems exist, but we will not discuss them during our course. I am ready to discuss this issue outside of school.
Question 6:
Do you think that knowledge is not as important as the ability to learn and analyze?
Answer: I personally believe that the most important is the ability to learn "how to learn." Therefore, for me knowledge is less important than the ability to apply mental structures in work. You can always get knowledge on the Internet, in databases, in other places; but you must have the ability to process information. If you do not know how to work with information, then you will never understand many things. For me, teaching methods are more important than knowledge.
Question 7:
Is there a difference between small and large projects in the field of software engineering? Do we need to apply different approaches to them?
Answer: There are two answers to these questions. Of course, there is a difference. The need for object-oriented development arose due to the complexity of managing large projects. For small projects, we do not see such a need. The second answer: during classes we will not be able to work with large projects, and we will apply the above mentioned methods to small projects. Of course, small projects are not always as well suited to this goal. However, the final answer is that we can use these techniques for both cases.
Question 8:
What do you think is the most important event in computer science in the last 10 years?
Answer: From a scientific point of view, there have been many discoveries, for example in the field of algorithms. However, they are not so important to the general public. The most visible and essential part of me, of course, is the distribution of social networks. They and mobile technologies are the most visible changes of the past decade. Twenty years ago, no one could have imagined that people would sit in a restaurant and pay more attention to their mobile device, rather than eating food and interacting with living people.
Full webinar entry:
Webinar Machine Learning, lecturer - Samir Belhauari
Question 1:
Over the past few years, many software libraries and environments have been created for Machine Learning researchers. However, in the field of hardware, we find only a few examples of special processors for digital data processing and machine learning. What are the most significant developments you could mention in recent years?
Answer: I was working on a project on the application of sensors and chips for the recognition and determination of gases based on Gaussian processes and a model of a mixture of normal distributions for machine learning. The SVM algorithm was applied in the form of hardware.
Question 2:
What do you think about skin cancer? Mortality rates from this species are less than from other dangerous cancers, while at the same time it is most suitable for machine recognition due to its visual symptoms.
Answer: Breast cancer and lung cancer are most common among women and men, and there is a lot of research concerning skin cancer and segmentation and diagnosis.
Question 3:
You mentioned a few subjects that need to be studied before proceeding to Machine Learning. Could you advise subjects that can be studied in parallel or after Machine Learning classes?
Answer: I will “refresh” students' knowledge of mathematics and algorithms before the start of our course, and will also provide additional materials that will allow a better understanding of the main concepts of the course.
Question 4:
What projects will students do during the course?
Answer: Students are required to know the fundamentals and algorithms of ML, as well as rewrite (understand) codes
Question 5:
As I understand it, the main goal of the course is to make the machine learn without programming itself through the process of generalization.
Answer: it may or may not be programmed, since some algorithms are dynamic, but some of which are not.
Question 6:
Do you think that the generalization of the extracted information is enough to create artificial intelligence?
A: I think this is not enough, as some applications require the use of innovative algorithms without data.
Question 7:
Some universities point out that some universities have succeeded in programming robots and computers for data aggregation. Is it possible to teach machines to make decisions, knowing their consequences in the future?
Answer: Of course, it is possible to teach computers to make the best decisions and conclusions; however, to accomplish this task, it is important to model our task in mathematical terms.
Question 8:
What literature would you recommend for beginners? What areas of mathematics are important for learning machine learning?
Answer: You need to know the following areas:
• Basic probability, matrices and calculus
• Familiarity with some programming language C / C ++ and MATLAB
Literature:
S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach, 3rd Edition, Prentice Hall (2010).
D.Koller and N.Friedman. Probabilistic Graphical Models, MIT Press (2009)
R. Sutton and A.Barto. Reinforcement Learning: An Introduction, MIT Press (1998)
E.Tsang. Foundations of constraint satisfaction. Academic Press (1993)
Full webinar entry:
Last week’s series of our webinars successfully crossed its equator, and today we want to announce the upcoming webinar, and also publish transcripts of the records of our listeners ’questions and the answers of our lecturers to them.
So, on March 11, at 18:00 (Moscow time), our professor Manuel Mazzara will hold a webinar on the topic of Theory of Algorithms (Theory of Computation). Hurry to register for the webinar on the link .
')
We remind you that the collection of applications for our undergraduate program continues.
Artificial Intelligence webinar, lecturer - Samir Belhauari
Question 1:
Professor, have you heard about the Human Brain project, whose goal is to create a simulation model of the human brain?
Answer: Yes, the HBP project is carried out by the university where I worked before - École polytechnique fédérale de Lausanne (EPFL-Switzerland). This project is funded by the European Union. They build a computer model of a real brain and thus try to learn all its secrets.
Question 2:
What languages are used in AI programming today?
Answer: It depends on the specific branch of AI (computer vision, machine learning, search, planning, robotics, natural language processing, etc.). I would say that you should choose the language that allows you to easily create prototypes of certain elements, for example, MATLAB. However, if you plan to build a system, then C or C ++ will be the best choice.
Question 3:
Could you give an example of how AI can be used in the oil and gas industry?
Answer: Today, artificial intelligence technologies are widely used in the modern oil industry, including oil and gas field simulations, optimization of drilling and production, drilling automation and process control in general.
Question 4:
What are the basic knowledge you need to have for successful learning in this subject?
Answer: You will need basic programming knowledge, Probability Theory, and Linear Algebra.
Question 5:
Does Markov Chain refer to dynamic programming?
Answer: Yes, it does. Markov chains are often used in solving problems of dynamic optimization.
Question 6:
Please tell me how well you need to understand the economy in order to develop AI mechanisms in this industry?
Answer: You need to know exactly what the economist wants from your model in order to develop an efficiently operating model. From the point of view of knowledge, I believe that you only need to know basic economic terms and general concepts.
Question 7:
What approaches exist in the field of computer vision for applications without a priori information. What ideas exist in the field of motion detection?
Answer: 1) The clustering algorithm will be used if there is no a priori information; 2) Motion detection works based on the frame differentiation method, which compares how the intensity of pixels changes its position from frame to frame. There are two options for motion detection: a) the first method considers changing the pattern as a whole; b) the second method considers the movement of the averaged array.
Question 8:
What can you say about the R language? I heard that he is quite popular in the field of machine learning. Is there a workshop on a programming language in the course itself?
Answer: The R language is often used because it is free and easily accessible on the web. I prefer to use MATLAB (we can add several tasks on the R language, if they wish). The course on Artificial Intelligence will have 5 tasks, during which students will be able to use MATLAB or C ++ for coding
Question 9:
Which of these organizations - IEEE or ACM has more authority in the field of Computer Science?
Answer: Both of these organizations are very authoritative.
Full webinar entry:
Artificial Cognitive Systems Webinar, lecturer - David Vernon
Question 1: Renat Shaikhutdinov
How do you test complex behaviors? For example, a simple function can be tested using unit tests, and what to do in this case?
Answer: The main problem is that cognitive systems deal with circumstances that cannot be fully detailed at the design stage, that is, it is assumed that cognitive systems face changing, unpredictable and non-integrity information. Testing these types of systems is extremely difficult. Of course, you can subject individual components to unit testing, but system testing is much more difficult. Most people solve this problem by testing the system in real conditions, observing how it interacts with animate and inanimate objects when looking at possible scenarios. You can do this in the laboratory by simulating a natural environment (for example, a kitchen), or test it in a natural environment, setting a task for it, and observing its behavior when it tries to perform a specific task.
Question 2: Viktor Smirnov
Professor Vernon, in your presentation you conceptually share learning and development. How common is this division in cognitive science and / or robotics?
Answer: The difference between training and development lies in the fact that during the course of training, an adaptation (calibration) of the model provided by a third-party subject occurs, and during development the subject creates his own model. Thus, training is based on determining the parameters of a model provided by another subject, while development is based on the independent creation of a model. This division is not yet so common in the scientific community, but it has proven very useful in explaining the technical methods and processes underlying both problems. Of course, there are other ways to separate learning and development. For example, training is usually focused on one skill or knowledge, while development involves the acquisition of a multitude of skills and knowledge and an understanding of their relationships. Also, learning often involves understanding how the world functions, often without considering the agent’s view of the situation. Development is always connected with the attitude of the abilities of the subject in the context of how the world functions. In psychology, development is a process that a subject goes through with the goal of expanding its set of possible actions and extending its time span for its prospecting ability (that is, its ability to anticipate events and the need to act).
Question 3: Anatoly Sviridenkov
Do you use any particular logic for knowledge? If so, what type? First order logic?
Answer: Most cognitive systems, such as Soar and ACT-R, use a production model, that is, they are rule-based systems with conditions and related actions. Although they do not use formal logic, they are, in essence, the application of first-order predicate calculus, that is, first-order logic. Emergent (from the English. Emergent - arising, unexpectedly appearing) cognitive systems do not denote knowledge using symbols and therefore do not use formal logic to justify or denote knowledge. Instead, they use commutative methods and associative techniques to present and operate information.
Question 4: Dmitry Chesnakov
In your presentation, are you talking about MOOC (mass open distance courses) or about the course at Innopolis University?
Answer: This is a course at Innopolis University. Professor Vernon will give the course “Artificial Cognitive Systems” in the second semester of the 2014-2015 school year.
Question 5: Viktor Smirnov
How important is the problem of modeling phenomenal consciousness in modern cognitive systems?
Answer: Opinions diverge. Some scientists believe that there is no need to use the concept of consciousness in the study of the process of knowledge. Others are convinced that this is an integral part of knowledge. What is exactly true is that the study of computational models of consciousness at the moment is a recognized area of study and the study of the process of cognition plays an important role. In my course, we will not address much of the topic of consciousness, only when studying various types of memory (procedural and declarative memory)
Question 6: Anatoly Sviridenkov
What do you think about deep learning in cognitive systems? Is it possible to combine character and sub-character levels?
Answer: Great question! Most of the scientific community believes that this is important. When I talked about cognitive architectures, I mentioned a cognitive and emergent approach. The combination of these two approaches is called hybrid cognitive architecture. There are many well-known hybrid cognitive architectures, such as CLARION and ACT-R. The basic idea is precisely what you propose: to combine symbolic and sub-symbolic forms of knowledge, that is, knowledge that is explicit and is represented by a symbolic system and knowledge that is implicit and is often represented using commutative techniques such as artificial neural networks.
Question 7: Anatoly Sviridenkov
In which area do you expect a breakthrough: brain modeling, machine learning, or artificial intelligence?
Answer: I think in the field of machine learning, but all three areas are very important. For example, a lot of research is currently being done on brain modeling. The results have already had an impact on several computing systems, such as the mirror neural system. Personally, I expect several key breakthroughs in the study of autonomous systems.
Question 8:
In your presentation, you pay great attention to various types of memory. Why does the machine have so many types of memory?
Answer: We need different types of memory to encode different types of knowledge. For example, there is declarative knowledge that relates to facts about the world (metals are hard, boiling water is very hot, etc.). Another type of knowledge is knowledge based on skills, the ability to do things. This is procedural knowledge. They are encoded in a separate type of memory and require different views when you create an artificial system. We call it procedural memory. There is also a short-term and long-term memory, the short-term memory stores knowledge only as long as it is necessary to perform a task, the long-term memory contains all the experience of the subject.
Full webinar entry:
Webinar Component-Based Software Engineering, lecturer - Manuel Mazzara
Question 1:
Today, companies and people operate with huge amounts of data. Companies at the same time accumulate the entire history of transactions, management information and other data. People save a lot of media data. But in real life there are no organisms capable of storing all sensory information. Is there a paradigm in the field of software development that deals with this issue?
Answer: As far as I know, such a paradigm does not exist now. This area is very new now. Big Data, Data Mining and to a certain extent Deep Web are areas that are related to the problem you mentioned.
Question 2:
Do you think computers and machines will surpass our abilities in the future if technology develops at such a pace? How can humankind prevent this, to always stay ahead.
Answer: My personal opinion is no. There are certain things that only a person can do; machines can never make them. The speed of technology development and the speed of machines have no relation to this. There are separate thought processes that machines simply cannot have. For example, computability and Turing-Church conjecture. Naturally, this is just my opinion. However, there is no evidence to the contrary. Some of my colleagues are confident that in 50 years we will have machines that are conscious. I'm not sure this will happen.
Question 3:
As far as I understand, we use component-based software engineering daily. Is there any difference between CBSE and traditional programming techniques?
Answer: The need for software decomposition into smaller components exists not only in the last 10 or 15 years, but much longer. At the very beginning of the development of computer science, it became obvious that big problems are more effectively solved if we divide them into small parts. CBSE is certainly part of Software Engineering. CBSE is an evolutionary development of previous concepts, such as structured programming and object-oriented development.
Question 4:
What areas of IT development are most important these days, and will be most important in the near future?
Today, cloud computing, Big Data and Data Mining are much discussed. With the advent of social networks, we have noticed a tremendous commercial interest in these areas (from Facebook, Twitter, etc.)
Answer: Another important aspect is the field of e-medicine, the technology in which is used to improve the quality of life of people, especially the elderly and with disabilities. We can help these people thanks to modern technology. For example, it can be implemented through mobile applications and devices. Personally, I plan to pay special attention to these areas in the future.
Question 5:
What do you think about really decentralized systems? For example, systems in which all links are interchangeable?
Answer: This question is very interesting. Such systems exist, but we will not discuss them during our course. I am ready to discuss this issue outside of school.
Question 6:
Do you think that knowledge is not as important as the ability to learn and analyze?
Answer: I personally believe that the most important is the ability to learn "how to learn." Therefore, for me knowledge is less important than the ability to apply mental structures in work. You can always get knowledge on the Internet, in databases, in other places; but you must have the ability to process information. If you do not know how to work with information, then you will never understand many things. For me, teaching methods are more important than knowledge.
Question 7:
Is there a difference between small and large projects in the field of software engineering? Do we need to apply different approaches to them?
Answer: There are two answers to these questions. Of course, there is a difference. The need for object-oriented development arose due to the complexity of managing large projects. For small projects, we do not see such a need. The second answer: during classes we will not be able to work with large projects, and we will apply the above mentioned methods to small projects. Of course, small projects are not always as well suited to this goal. However, the final answer is that we can use these techniques for both cases.
Question 8:
What do you think is the most important event in computer science in the last 10 years?
Answer: From a scientific point of view, there have been many discoveries, for example in the field of algorithms. However, they are not so important to the general public. The most visible and essential part of me, of course, is the distribution of social networks. They and mobile technologies are the most visible changes of the past decade. Twenty years ago, no one could have imagined that people would sit in a restaurant and pay more attention to their mobile device, rather than eating food and interacting with living people.
Full webinar entry:
Webinar Machine Learning, lecturer - Samir Belhauari
Question 1:
Over the past few years, many software libraries and environments have been created for Machine Learning researchers. However, in the field of hardware, we find only a few examples of special processors for digital data processing and machine learning. What are the most significant developments you could mention in recent years?
Answer: I was working on a project on the application of sensors and chips for the recognition and determination of gases based on Gaussian processes and a model of a mixture of normal distributions for machine learning. The SVM algorithm was applied in the form of hardware.
Question 2:
What do you think about skin cancer? Mortality rates from this species are less than from other dangerous cancers, while at the same time it is most suitable for machine recognition due to its visual symptoms.
Answer: Breast cancer and lung cancer are most common among women and men, and there is a lot of research concerning skin cancer and segmentation and diagnosis.
Question 3:
You mentioned a few subjects that need to be studied before proceeding to Machine Learning. Could you advise subjects that can be studied in parallel or after Machine Learning classes?
Answer: I will “refresh” students' knowledge of mathematics and algorithms before the start of our course, and will also provide additional materials that will allow a better understanding of the main concepts of the course.
Question 4:
What projects will students do during the course?
Answer: Students are required to know the fundamentals and algorithms of ML, as well as rewrite (understand) codes
Question 5:
As I understand it, the main goal of the course is to make the machine learn without programming itself through the process of generalization.
Answer: it may or may not be programmed, since some algorithms are dynamic, but some of which are not.
Question 6:
Do you think that the generalization of the extracted information is enough to create artificial intelligence?
A: I think this is not enough, as some applications require the use of innovative algorithms without data.
Question 7:
Some universities point out that some universities have succeeded in programming robots and computers for data aggregation. Is it possible to teach machines to make decisions, knowing their consequences in the future?
Answer: Of course, it is possible to teach computers to make the best decisions and conclusions; however, to accomplish this task, it is important to model our task in mathematical terms.
Question 8:
What literature would you recommend for beginners? What areas of mathematics are important for learning machine learning?
Answer: You need to know the following areas:
• Basic probability, matrices and calculus
• Familiarity with some programming language C / C ++ and MATLAB
Literature:
S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach, 3rd Edition, Prentice Hall (2010).
D.Koller and N.Friedman. Probabilistic Graphical Models, MIT Press (2009)
R. Sutton and A.Barto. Reinforcement Learning: An Introduction, MIT Press (1998)
E.Tsang. Foundations of constraint satisfaction. Academic Press (1993)
Full webinar entry:
Source: https://habr.com/ru/post/215039/
All Articles