Introduction

  1. Intro to Deep Learning
  2. Linear algebra and probability basics :)
  3. Machine learning basics whole folder to write! classical algorithms such as Bayes ecc, least squares…, use The general framwork, The bayesian setting.
  4. Cross Entropy
  5. Kullback-Leibler divergence
  6. Linear regression
  7. Logistic regression
  8. Machine Learning basics
  9. No Free Lunch Theorem
  10. ReLu
  11. Residual networks
  12. Dataset Augmentation
  13. Batch normalization

Neural Networks

  1. Neural Networks: from machine learning to deep learning
  2. Training Neural Networks: Overfitting and underfitting, Stochastic gradient descent SGD, Vanishing and exploding gradient
  3. Automatic differentiation and Pytorch.

Deep Learning Architectures

  1. Convolutions from first principles, CNN
  2. RNN
  3. Tokenization, The Encoder-Decoder framework, Transformer, Word2Vec

Deep Learning Applications

  1. Transfer Learning, Transfer Learning in NLP
  2. Self-Supervised Learning, Deep Metric Learning
  3. GAN
  4. Language models
  5. Generative models