NYU Deep Learning SP21
5.0
(3)
21 learners
What you'll learn
This course includes
- 47.3 hours of video
- Certificate of completion
- Access on mobile and TV
Course content
1 modules • 33 lessons • 47.3 hours of video
NYU Deep Learning SP21
33 lessons
• 47.3 hours
NYU Deep Learning SP21
33 lessons
• 47.3 hours
- 01 – History and resources 50:18
- 01L – Gradient descent and the backpropagation algorithm 01:51:04
- 02 – Neural nets: rotation and squashing 01:01:54
- 02L – Modules and architectures 01:42:27
- 03 – Tools, classification with neural nets, PyTorch implementation 01:05:48
- 03L – Parameter sharing: recurrent and convolutional nets 01:59:48
- 04L – ConvNet in practice 51:41
- 04.1 – Natural signals properties and the convolution 01:09:13
- 04.2 – Recurrent neural networks, vanilla and gated (LSTM) 01:05:36
- 05L – Joint embedding method and latent variable energy based models (LV-EBMs) 01:51:31
- 05.1 – Latent Variable Energy Based Models (LV-EBMs), inference 01:01:05
- 05.2 – But what are these EBMs used for? 10:42
- 06L – Latent variable EBMs for structured prediction 01:48:54
- 06 – Latent Variable Energy Based Models (LV-EBMs), training 01:04:49
- 07L – PCA, AE, K-means, Gaussian mixture model, sparse coding, and intuitive VAE 01:54:23
- 07 – Unsupervised learning: autoencoding the targets 56:42
- 08L – Self-supervised learning and variational inference 01:54:44
- 08 – From LV-EBM to target prop to (vanilla, denoising, contractive, variational) autoencoder 01:00:35
- 09L – Differentiable associative memories, attention, and transformers 02:00:29
- 09 – AE, DAE, and VAE with PyTorch; generative adversarial networks (GAN) and code 01:07:51
- 10L – Self-supervised learning in computer vision 01:36:13
- 10 – Self / cross, hard / soft attention and the Transformer 01:12:01
- 11L – Speech recognition and Graph Transformer Networks 01:55:04
- 11 – Graph Convolutional Networks (GCNs) 57:34
- 12L – Low resource machine translation 01:57:56
- 12 – Planning and control 01:10:23
- 13L – Optimisation for Deep Learning 01:51:33
- 13 – The Truck Backer-Upper 01:01:22
- 14L – Lagrangian backpropagation, final project winners, and Q&A session 02:12:36
- 14 – Prediction and Planning Under Uncertainty 01:14:45
- AI2S Xmas Seminar - Dr. Alfredo Canziani (NYU) - Energy-Based Self-Supervised Learning 03:45:28
- 09P – Contrastive joint embedding methods (JEMs) for self-supervised learning (SSL) 56:52
- 10P – Non-contrastive joint embedding methods (JEMs) for self-supervised learning (SSL) 01:05:28
Take this course with you
Download the app to continue lessons from your phone anytime.
