Deep Learning

Deep learning course covers theoretical and practical aspects, state-of-the-art deep learning architectures, and application examples.

Topics covered:
1. Introduction to Deep Learning (High-level definitions of fundamental concepts and first examples)
2. Deep Learning components (gradient descent models, loss functions, avoiding over-fitting, introducing asymmetry)
3. Feed forward neural networks
4. Convolutional neural networks
5. Embeddings (pre-trained embeddings, examples of pre-trained models, e.g., GloVe embeddings, Word2Vec)
6. Recurrent neural networks
7. Long-short term memory units
8. Advanced architectures (Densely connected networks, Adaptive structural learning)