Course Objectives
- To introduce theory of Markov decision problems and reinforcement learning
- To introduce different reinforcement learning techniques
- To implement different reinforcement learning techniques to various problems
- To introduce performance evaluation of reinforcement learning techniques
Topics
- Fundamentals of artificial neural networks
- Single layer neural networks, learning rules
- Multilayer neural networks
- Convolution neural networks
- Recurrent neural networks, long-short term memory
- Restricted Boltzmann Machines
- Deep learning applications
- Regresssion analysis with deep learning
- Classification analysis with deep learning
- Forecasting with deep learning
- Deep learning with unstructured data
