Completed
Week 11 – Lecture: PyTorch activation and loss functions
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
NYU Deep Learning - Spring 2020
Automatically move to the next video in the Classroom when playback concludes
- 1 Week 1 – Lecture: History, motivation, and evolution of Deep Learning
- 2 Week 1 – Practicum: Classification, linear algebra, and visualisation
- 3 Week 2 – Lecture: Stochastic gradient descent and backpropagation
- 4 Week 2 – Practicum: Training a neural network
- 5 Week 3 – Lecture: Convolutional neural networks
- 6 Week 3 – Practicum: Natural signals properties and CNNs
- 7 Week 4 – Practicum: Listening to convolutions
- 8 Week 5 – Lecture: Optimisation
- 9 Week 5 – Practicum: 1D multi-channel convolution and autograd
- 10 Week 6 – Lecture: CNN applications, RNN, and attention
- 11 Week 6 – Practicum: RNN and LSTM architectures
- 12 Week 7 – Lecture: Energy based models and self-supervised learning
- 13 Week 7 – Practicum: Under- and over-complete autoencoders
- 14 Week 8 – Lecture: Contrastive methods and regularised latent variable models
- 15 Week 8 – Practicum: Variational autoencoders
- 16 Week 9 – Lecture: Group sparsity, world model, and generative adversarial networks (GANs)
- 17 Week 9 – Practicum: (Energy-based) Generative adversarial networks
- 18 Week 10 – Lecture: Self-supervised learning (SSL) in computer vision (CV)
- 19 Week 10 – Practicum: The Truck Backer-Upper
- 20 Week 11 – Lecture: PyTorch activation and loss functions
- 21 Week 11 – Practicum: Prediction and Policy learning Under Uncertainty (PPUU)
- 22 Week 12 – Lecture: Deep Learning for Natural Language Processing (NLP)
- 23 Week 12 – Practicum: Attention and the Transformer
- 24 Week 13 – Lecture: Graph Convolutional Networks (GCNs)
- 25 Week 13 – Practicum: Graph Convolutional Neural Networks (GCN)
- 26 Week 14 – Lecture: Structured prediction with energy based models
- 27 Week 14 – Practicum: Overfitting and regularization, and Bayesian neural nets
- 28 Week 15 – Practicum part A: Inference for latent variable energy based models (EBMs)
- 29 Week 15 – Practicum part B: Training latent variable energy based models (EBMs)
- 30 Matrix multiplication, signals, and convolutions
- 31 Supervised and self-supervised transfer learning (with PyTorch Lightning)
