Introduction §
- Intro to Deep Learning
- Linear algebra and probability basics :)
- Machine learning basics whole folder to write! classical algorithms such as Bayes ecc, least squares…, use The general framwork, The bayesian setting.
- Cross Entropy
- Kullback-Leibler divergence
- Linear regression
- Logistic regression
- Machine Learning basics
- No Free Lunch Theorem
- ReLu
- Residual networks
- Dataset Augmentation
- Batch normalization
Neural Networks §
- Neural Networks: from machine learning to deep learning
- Training Neural Networks: Overfitting and underfitting, Stochastic gradient descent SGD, Vanishing and exploding gradient
- Automatic differentiation and Pytorch.
Deep Learning Architectures §
- Convolutions from first principles, CNN
- RNN
- Tokenization, The Encoder-Decoder framework, Transformer, Word2Vec
Deep Learning Applications §
- Transfer Learning, Transfer Learning in NLP
- Self-Supervised Learning, Deep Metric Learning
- GAN
- Language models
- Generative models