01:07

Chapter 2, video 4–6

58:59

06 – Optimisation and gradient ascent

59:12

05 – Multi-class perceptron, binary and multi-class logistic regression

56:05

04 – Binary classifier evaluation, binary Perceptron

00:46

Chapter 1, video 1–3

01:00:36

03 – Naïve Bayes parameters estimation and Laplace smoothing

01:06:41

02 – Discrete probability recap, Naïve Bayes classification

02:48

00 – Course introduction

01:05:08

01 – Course first part recap, Naïve Bayes intro

01:43:43

14 – From latent-variable EBM (K-means, sparse coding) to target prop to autoencoders, step-by-step

53:14

07 – Classification, an energy perspective – PyTorch 5-step training code

01:47:39

06 – Classification, an energy perspective – Backprop and contrastive learning

50:30

05 – Classification, an energy perspective – Notation and introduction

01:07:19

03 – Inference with neural nets

02:09

00 – Intro to NYU Deep Learning Fall 2022 playlist

01:05:28

10P – Non-contrastive joint embedding methods (JEMs) for self-supervised learning (SSL)

56:52

09P – Contrastive joint embedding methods (JEMs) for self-supervised learning (SSL)

02:12:36

14L – Lagrangian backpropagation, final project winners, and Q&A session

01:51:32

13L – Optimisation for Deep Learning

01:54:23

07L – PCA, AE, K-means, Gaussian mixture model, sparse coding, and intuitive VAE

01:54:44

08L – Self-supervised learning and variational inference

02:00:29

09L – Differentiable associative memories, attention, and transformers

01:14:45

14 – Prediction and Planning Under Uncertainty

01:48:54

06L – Latent variable EBMs for structured prediction

01:51:31

05L – Joint embedding method and latent variable energy based models (LV-EBMs)

01:01:22

13 – The Truck Backer-Upper

51:41

04L – ConvNet in practice

01:59:48

03L – Parameter sharing: recurrent and convolutional nets

01:42:27

02L – Modules and architectures

01:51:04

01L – Gradient descent and the backpropagation algorithm

01:10:23

12 – Planning and control

01:57:56

12L – Low resource machine translation

57:34

11 – Graph Convolutional Networks (GCNs)

01:36:13

10L – Self-supervised learning in computer vision

01:55:04

11L – Speech recognition and Graph Transformer Networks

01:12:01

10 – Self / cross, hard / soft attention and the Transformer

01:07:51

09 – AE, DAE, and VAE with PyTorch; generative adversarial networks (GAN) and code

01:00:35

08 – From LV-EBM to target prop to (vanilla, denoising, contractive, variational) autoencoder

56:42

07 – Unsupervised learning: autoencoding the targets

50:18

01 – History and resources

02:10

Behind the scenes

01:04:49

06 – Latent Variable Energy Based Models (LV-EBMs), training

10:42

05.2 – But what are these EBMs used for?

01:01:05

05.1 – Latent Variable Energy Based Models (LV-EBMs), inference

01:05:36

04.2 – Recurrent neural networks, vanilla and gated (LSTM)

01:09:13

04.1 – Natural signals properties and the convolution

01:01:54

02 – Neural nets: rotation and squashing

01:05:48

03 – Tools, classification with neural nets, PyTorch implementation

01:11:24

Supervised and self-supervised transfer learning (with PyTorch Lightning)

58:57

Week 15 – Practicum part B: Training latent variable energy based models (EBMs)

59:05

Week 15 – Practicum part A: Inference for latent variable energy based models (EBMs)

47:02

Matrix multiplication, signals, and convolutions

01:11:28

Week 14 – Practicum: Overfitting and regularization, and Bayesian neural nets

02:07:31

Week 14 – Lecture: Structured prediction with energy based models

02:00:23

Week 13 – Lecture: Graph Convolutional Networks (GCNs)

01:10:02

Week 13 – Practicum: Graph Convolutional Neural Networks (GCN)

01:40:57

Week 12 – Lecture: Deep Learning for Natural Language Processing (NLP)

01:18:02

Week 12 – Practicum: Attention and the Transformer

01:53:44

Week 11 – Lecture: PyTorch activation and loss functions

01:23:19

Week 11 – Practicum: Prediction and Policy learning Under Uncertainty (PPUU)