LECTURES 2017 - 2018






This course includes 28 lectures, 14 laboratory classes, and 14 project classes.

dogagechallenge award certified to adrian horzyk and efe ergun 2nd winner h400 (234 kB) Certificate of International Summer School on Deep Learning for Adrian Horzyk COURSERA Certificate Deep Learning Specialization Neural Networks and Deep Learning for Adrian Horzyk COURSERA Certificate Deep Learning Specialization Improving Deep Neural Networks for Adrian Horzyk COURSERA Certificate Deep Learning Specialization Structuring Machine Learning Projects for Adrian Horzyk COURSERA Certificate Deep Learning Specialization Sequence Models for Adrian Horzyk

Due to the coronavirus threat and the temporal suspension of classes at the university, we must continue our lectures and classes remotely on-line.

I have prepared lectures for you on this website and I'm still working and preparing the next lectures for you during the semester. Please, try to go through the shared presentations on this website and to your best for the development of your knowledge. You must take control and responsibility for your development. I only can help you as much as it is possible in this difficult situation.

Laboratory classes will run remotely. You can try to accomplish the prepared assignments on-line working in your place.

If you have any troubles, you can consult them with me via e-mail or using Skype.

I anticipate that the coronavirus will not allow us to meet again at the university this semester, so please be prepared that we must work remotely, contacting via e-mail, Skype, or any other possible options. Your assignments will be also graded remotely when you send the presentations and codes to me.

Please, go through all the lectures (not only the new ones from 2020).

We start working in MS Teams where your assignments are prepared. In order to work in MS Teams, you need to have an account (e-mail) in the AGH domain. If you have one, please go to your MS Team space or join the class team using code "id77mxf" in MS Teams and start working. New lectures, assignments, and tests will appear in the MS Teams space soon and this space will also be used as a platform to upload your finished laboratory and project assignments to be graded. We will use the on-line presentation mode for some lectures that will be announced soon and to do your final presentations at the end of the semester, so please make you familiar with this team project environment. If something does not work or you have any suggestions, please write to me on my e-mail. The first welcome quiz is waiting for you!

What is this course about?

This course is intended to give students a broad overview and deep knowledge about popular solutions and efficient neural network models as well as to learn how to construct and train intelligent learning systems in order to use them in everyday life and work. During the course we will deal with the popular and most efficient models and methods of neural networks, fuzzy systems and other learning systems that enable us to find specific highly generalizing models solving difficult tasks. We will also tackle with various CI and AI problems and work with various data and try to model their structures in such a way to optimize operations on them throughout making data available without necessity to search for them. This is a unique feature of associative structures and systems. These models and methods will allow us to form and represent knowledge in a modern and very efficient way which will enable us to mine it and automatically draw conclusions. You will be also able to understand solutions associated with various tasks of motivated learning and cognitive intelligence.

Maybe you would like to take part in IT competitions (e.g. Kaggle) and win a lot of money?!

Today, computational intelligence (CI), machine learning (ML), data mining (DM), and artificial intelligence (AI) achieved already a lot! We have many interesting methods, models and computational tools which let us adapt CI models to many practical tasks. The CI professionals can earn even a six-figure salary for their work, but it is only a tip of the iceberg! We can still achieve a great development in artificial intelligence can be still far more intelligent than we meet today. Today, we rather develop intelligently adapting computational tools than real artificial intelligence! Artificial Intelligence (AI) can do much more and without so much effort from the people's point of view. It must be embodied and equipped with some smartly motivational mechanisms and associative properties (known from our brains) which let it achieve an adequate level.

Lectures will be supplemented by laboratory and project classes during which you will train and adapt the models learned during the lectures on various data using self-developed applications and existing modern programistic tools like RapidMiner, TensorFlow, Keras and Jupiter Notebook. Your hard work and practice will enable you not only to obtain expert knowledge and skills but also to develop your own intelligent learning system implementing a few of the most popular and efficient CI methods.

Expected results of taking a part in this course:

  • Broad knowledge of neural networks, associative and fuzzy systems as well as other intelligent learning systems.
  • Novel experience and broaden skills in construction, adaptation and training of neural networks and fuzzy systems.
  • Ability to construct intelligent learning systems of various kinds, especially deep learning solutions using modern Python 3 and libraries like TensorFlow, Keras and Jupiter Notebook.
  • Good and modern practices in modeling, construction, learning and generalization using developed and other tools like RapidMiner, TensorFlow, Keras and Jupiter Notebook.
  • Own intelligent learning system to use in your life or work.
  • Satisfaction of enrollment to this course.

How about looking inside the brain and associative processes? What do associated and associations mean?
How to model knowledge and intelligence?
How to create artificial intelligence?

I encourage you to bring your laptops to the laboratory classes so that you can work in your favorite programming environment and language and easily continue the work after finishing the classes. I would like you to take real advantages and skills from what you learn and implement during this course!

When does the course begin and what is the schedule of activities?

You can find information in the course schedule.

Students are invited to broaden their excellent projects from the project classes to their Master's theses and even scientific papers with help and contribution of the lecturer.

However lectures are generally not obligatory every student who enrolled in this course is invited to take a part in possibly all lectures which will be very intensive and full of news! The presented topics during lectures will be practically accomplished in the laboratory and project classes, so be conscious that the absence in the lectures will cause serious difficulties in the implementation of methods and accomplishing of tasks during the laboratory and project classes that will be evaluated after achieved results, implemented methods, and their quality. This course will be as much interesting, innovative, and valuable for you as the frequency and numerous presence of the participating students. Thus, all participating students are asked to organize their weekly schedule in such a way to be able to take a part in all course activities including lectures! Moreover, your ideas, whishes, and proposals can be also included and used in this course. We can do this course fascinating only together!

We start our classes with laboratory classes, followed by project classes. During the laboratory classes, you will implement the selected and the topmost practically promising tasks in the programming language you like. You can use computers and programming languages installed in the laboratory (Python, C#, C++, Java) or can use your computers together with your compilers and programming languages you prefer. During the project classes, you will implement the selected project that will substantially expand the chosen laboratory class task or will be a new one after your selection from the list of the proposed projects. However, we can also consider your proposals that will be ambitious enough.

Manifesto for Polish Artificial Intelligence

How this course will be graded?

Detailed information will be presented at the beginning of this course, i.e. during the first lecture, as well as during the first laboratory classes and the first project classes.

The presentations of students' final projects and laboratory tasks will be carried out on 19th June.
All students are invited to come to all your final presentations together in order to learn from your fascinating works, results and presentation!
Please, do not forget to take with all components (the solved tasks, the final project, applications, source codes, data, databases, sources, the final presentation etc.) which proof your self-execution of all tasks and the project as well as the hopefully positive grades that you will get!