SUBJECTS

MACHINE LEARNING, COMPUTATIONAL INTELLIGENCE, AND SOFT COMPUTING

Machine learning is the part of computer science that is responsible for getting computers to act without being explicitly programmed. I introduce the core idea of teaching a computer to learn various concepts and rules using data patterns without being explicitly programmed.

This course provides a broad introduction to machine learning. You can get known also about computational intelligence, soft computing, data mining, statistical pattern recognition and classification. In this class, you will learn about the most effective machine learning and soft computing techniques, gain practice implementing them, and getting them to work for yourself. You will learn the theoretical underpinnings of learning as well as gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. The most important topics of this course include:

  1. Supervised learning: parametric and non-parametric algorithms, support vector machines, kernels, and artificial neural networks.
  2. Unsupervised learning: clustering, dimensionality reduction, and deep learning.
  3. Best practices in machine learning, e.g.: bias and variance theory, innovation processes in machine learning and artificial intelligence.

The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to build smart intelligent robots with perception, recognition, classification, and control mechanisms, text understanding for intelligent web search, anti-spam filters, computer vision, biomedical tasks, audio, and database mining.

XXX

xxxxx...

XXX

xxxxx...

XXX

xxxxx...

XXX

xxxxx...

XXX

xxxxx...

XXX

xxxxx...

Interesting links and extra materials to study:
  1. Ryszard Tadeusiewicz, Discovering neural network proprieties by means of C# programs, 2009.
  2. Horzyk, A., Artificial Associative Systems and Associative Artificial Intelligence (language: Polish), Academic Publishing House EXIT, Warsaw, 2013, postdoctoral monograph, pp. 1-280.
  3. Machine Learning Course by Stanford University