Course description
Introduction to Deep Learning. Concepts and main networks. Use cases in classification, regression, transfert learning, dimension reduction, data generation.
Syllabus
- Introduction to deep learning and to development tools (Tensorflow with Keras and Google colab )
- Perceptrons and MultiLayer Perceptrons
- Convolutional Networks
- Autoencoders
- RNN, LSTM and GRU
- Attention mechanisms and transformers
- Transfert Learning
- Generative models - GAN, VAE and diffusion
- Graph neural networks