Attention in Encoder-Decoder architecture
Encoder-Decoder architecture bottleneck. Attention mechanism.

Transformers in NLP
Attention is all you need example. Transformers as another approach to NLP tasks.

Unsupervised Deep Learning part 2
Variational autoencoders. Connections to Generative adversarial networks.

Unsupervised approaches in Deep Learning
Dimensionality reduction, denoising and data transformation using autoencoders. Similarities to PCA.

Midterm test

Introduction to Reinforcement Learning
Reinforcement Learning problem statement. Stochastic and black box optimisation.

Convolutional neural networks in text classification
CNN approach to context analysis. Similarities and differences from RNN.

Recurrent neural networks, seq2seq
Sequential modeling. Encoder-decoder architecture.

Word embeddings 
Word representations in Machine Learning. Classical approach. Embeddings. Word2vec.

Text classification tasks
Text classification using in Machine Learning and Deep Learning.

Model free learning. Q-learning, SARSA
On policy and off policy algorithms. N-step algorithms.

Value based methods in RL
Discounted reward in RL. Value iteration. Policy iteration.

Approximate Q-learning
Value function approximation using complex functions and neural networks. DQN. Experience replay.

Policy gradient methods
Policy gradient. REINFORCE algorithm. Advanced actor critic.

Final exam