Deep Learning Systems
Description
This course is an introduction to the development and application of deep learning neural networks. The topics covered in the course include shallow and deep neural networks for classification and prediction, convolutional neural networks, recurrent neural networks, deep unsupervised and reinforcement learning, and applications to real world problem domains.
Aim of the course
Provide the student with the theoretical and practical knowledge of deep artificial neural network and application for real worl problems.
Prerequisites
Basic knowledge of programming, probability theory, statistics and linear algebra.
Course content
1. History and recent achievements in artificial intelligence development. Ethics and artificial intelligence.
2. Data preparation.
3. Types of learning: supervised, unsupervised, reinforcement learning.
4. Supervised learning: linear regression, binary logistic regression, decision tree. Assessment of classification and prediction accuracy.
5. Unsupervised learning: k-means clustering, hierarchical clustering, principal component analysis.
6. Methods of feature selection.
7. Neural networks and error back-propagation training algorithm.
8. Convolutional neural networks.
9. Recurrent neural networks for sequence analysis.
10. Reinforcement Learning: Deep Q-networks.
10. Neural network training algorithms. Methods to prevent overtraining.
11. Complex structures of artificial neural networks.
Assesment Criteria
1. Ability to bring different topics presented in the material together
2. Ability to compare different methods of artificial neural networks
3. Practical demonstration of knowledge of artificial neural networks methods and skills in choosing appropriate artificial neural networks methods for a given problem.
4. Practical demonstration the ability to manipulate with implementations of artificial neural networks methods in order to solve the problem in some field of application given by a teacher.
5. Meaningfully explanation of the application of artificial neural networks solution of an applied problem.
6. Mini-project result presentation to colleagues and the lecturer.
