Deep Learning Course (NYU, Spring 2020) Yann Lecun

Deep Learning course at NYU, Spring 2020. Taught by Yann LeCun & Alfredo Canziani. With practical applications using PyTorch.

Turing Award winner tells you about deep learning

• Chapter 1：Week 1 – Lecture- History, motivation, and evolution of Deep Learning (1 hours and 38 minutes and 56 seconds)

• Chapter 2：Week 1 – Practicum- Classification, linear algebra, and visualisation (52 minutes and 30 seconds)

• Chapter 3：Week 2 – Lecture- Stochastic gradient descent and backpropagation (1 hours and 43 minutes and 16 seconds)

• Chapter 4：Week 2 – Practicum- Training a neural network (56 minutes and 59 seconds)

• Chapter 5：Week 3 – Lecture- Convolutional neural networks (1 hours and 38 minutes and 15 seconds)

• Chapter 6：Week 3 – Practicum- Natural signals properties and CNNs (48 minutes and 21 seconds)

• Chapter 7：Week 4 – Practicum- Listening to convolutions (51 minutes and 1 seconds)

• Chapter 8：Week 5 – Lecture- Optimisation (1 hours and 29 minutes and 5 seconds)

• Chapter 9：Week 5 – Practicum- 1D multi-channel convolution and autograd (44 minutes and 58 seconds)

• Chapter 10：Week 6 – Lecture- CNN applications, RNN, and attention (1 hours and 28 minutes and 47 seconds)

• Chapter 11：Week 6 – Practicum- RNN and LSTM architectures (53 minutes and 33 seconds)

• Chapter 12：Week 7 – Practicum- Under- and over-complete autoencoders (55 minutes and 3 seconds)

• Chapter 13：Week 7 – Lecture- Energy based models and self-supervised learning (1 hours and 37 minutes and 18 seconds)

• Chapter 14：Week 8 – Lecture- Contrastive methods and regularised latent variable models (1 hours and 39 minutes and 25 seconds)

• Chapter 15：Week 8 – Practicum- Variational autoencoders (58 minutes and 4 seconds)

• Chapter 16：Week 9 – Lecture- Group sparsity, world model, and generative adversarial networks (GANs) (1 hours and 58 minutes and 24 seconds)

• Chapter 17：Week 9 – Practicum- (Energy-based) Generative adversarial networks (1 hours and 15 minutes and 11 seconds)

• Chapter 18：Week 10 – Practicum- The Truck Backer-Upper (1 hours and 25 seconds)

• Chapter 19：Week 10 – Lecture- Self-supervised learning (SSL) in computer vision (CV) (2 hours and 41 seconds)

• Chapter 20：Week 11 – Practicum- Prediction and Policy learning Under Uncertainty (PPUU) (1 hours and 23 minutes and 18 seconds)

• Chapter 21：Week 11 – Lecture- PyTorch activation and loss functions (1 hours and 53 minutes and 44 seconds)

• Chapter 22：Week 12 – Practicum- Attention and the Transformer (1 hours and 18 minutes and 1 seconds)

• Chapter 23：Week 12 – Lecture- Deep Learning for Natural Language Processing (NLP) (1 hours and 40 minutes and 56 seconds)

• Chapter 24：Week 13 – Practicum- Graph Convolutional Neural Networks (GCN) (1 hours and 10 minutes and 1 seconds)

• Chapter 25：Week 13 – Lecture- Graph Convolutional Networks (GCNs) (2 hours and 22 seconds)

• Chapter 26：Week 14 – Lecture- Structured prediction with energy based models (2 hours and 7 minutes and 30 seconds)

• Chapter 27：Week 14 – Practicum- Overfitting and regularization, and Bayesian neural nets (1 hours and 11 minutes and 27 seconds)

• Chapter 28：Week 15 – Practicum part A- Inference for latent variable energy based models (EBMs) (59 minutes and 4 seconds)

• Chapter 29：Week 15 – Practicum part B- Training latent variable energy based models (EBMs) (58 minutes and 56 seconds)

• Chapter 30：Matrix multiplication, signals, and convolutions (47 minutes and 1 seconds)

• Chapter 31：Supervised and self-supervised transfer learning (with PyTorch Lightning) (1 hours and 11 minutes and 23 seconds)

• Chapter 32：Four decades in Machine Learning- a Personal Journey by Yann LeCun (1 hours and 31 minutes and 22 seconds)