Completed
13L – Optimisation for Deep Learning
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
NYU Deep Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 01 – History and resources
- 2 01L – Gradient descent and the backpropagation algorithm
- 3 02 – Neural nets: rotation and squashing
- 4 02L – Modules and architectures
- 5 03 – Tools, classification with neural nets, PyTorch implementation
- 6 03L – Parameter sharing: recurrent and convolutional nets
- 7 04L – ConvNet in practice
- 8 04.1 – Natural signals properties and the convolution
- 9 04.2 – Recurrent neural networks, vanilla and gated (LSTM)
- 10 05L – Joint embedding method and latent variable energy based models (LV-EBMs)
- 11 05.1 – Latent Variable Energy Based Models (LV-EBMs), inference
- 12 05.2 – But what are these EBMs used for?
- 13 06L – Latent variable EBMs for structured prediction
- 14 06 – Latent Variable Energy Based Models (LV-EBMs), training
- 15 07L – PCA, AE, K-means, Gaussian mixture model, sparse coding, and intuitive VAE
- 16 07 – Unsupervised learning: autoencoding the targets
- 17 08L – Self-supervised learning and variational inference
- 18 08 – From LV-EBM to target prop to (vanilla, denoising, contractive, variational) autoencoder
- 19 09L – Differentiable associative memories, attention, and transformers
- 20 09 – AE, DAE, and VAE with PyTorch; generative adversarial networks (GAN) and code
- 21 10L – Self-supervised learning in computer vision
- 22 10 – Self / cross, hard / soft attention and the Transformer
- 23 11L – Speech recognition and Graph Transformer Networks
- 24 11 – Graph Convolutional Networks (GCNs)
- 25 12L – Low resource machine translation
- 26 12 – Planning and control
- 27 13L – Optimisation for Deep Learning
- 28 13 – The Truck Backer-Upper
- 29 14L – Lagrangian backpropagation, final project winners, and Q&A session
- 30 14 – Prediction and Planning Under Uncertainty
- 31 AI2S Xmas Seminar - Dr. Alfredo Canziani (NYU) - Energy-Based Self-Supervised Learning
