Introduction of students to artificial intelligence with emphasis on modern approaches (deep learning and reinforcement learning). The course focuses on a practical part with concrete examples for the application of the presented approaches.

1. ARTIFICIAL INTELLIGENCE (AI) – INTRODUCTION
• What is AI
• History of AI
• Risks and Benefits of AI
• Some applications
2. LEARNING FROM EXAMPLES
3. DEEP LEARNING
• Simple Feedforward Networks
• Input encoding
• Output layers and loss functions
• Hidden layers
• Learning algorithms
• Generalization
• Convolutional Neural Networks (CNN)
• Recurrent Neural Networks (RNN)
4. INTELLIGENT AGENTS
5. REINFORCEMENT LEARNING
• Learning from rewards (Markov decision process)
• Passive reinforcement learning
• Active reinforcement learning
• Generalization
6. EXAMPLES:
• Example of use of neural networks
• Using regular convolutional neural networks for face and facial expression recognition with deep face – part 1
• Using regular convolutional neural networks for face recognition and facial expression with deep face – part 2
• Reinforcement Learning with Python (gym) – how to land lunar module on moon - part 1
• Reinforcement Learning with Python (gym) - how to get mount car to the top of the hill – part 2