Course Hive
Courses
Summaries
Continue with Google
or

Deep Learning Course (NYU, Spring 2020)

5.0 (0)
8 learners

What you'll learn

This course includes

  • 42.5 hours of video
  • Certificate of completion
  • Access on mobile and TV

Course content

1 modules • 32 lessons • 42.5 hours of video

Deep Learning Course (NYU, Spring 2020)

32 lessons • 42.5 hours
  • Week 1 – Lecture: History, motivation, and evolution of Deep Learning01:38:57
  • Week 1 – Practicum: Classification, linear algebra, and visualisation52:31
  • Week 2 – Lecture: Stochastic gradient descent and backpropagation01:43:17
  • Week 2 – Practicum: Training a neural network57:00
  • Week 3 – Lecture: Convolutional neural networks01:38:16
  • Week 3 – Practicum: Natural signals properties and CNNs48:22
  • Week 4 – Practicum: Listening to convolutions51:02
  • Week 5 – Lecture: Optimisation01:29:06
  • Week 5 – Practicum: 1D multi-channel convolution and autograd44:59
  • Week 6 – Lecture: CNN applications, RNN, and attention01:28:48
  • Week 6 – Practicum: RNN and LSTM architectures53:34
  • Week 7 – Practicum: Under- and over-complete autoencoders55:04
  • Week 7 – Lecture: Energy based models and self-supervised learning01:37:19
  • Week 8 – Lecture: Contrastive methods and regularised latent variable models01:39:26
  • Week 8 – Practicum: Variational autoencoders58:05
  • Week 9 – Lecture: Group sparsity, world model, and generative adversarial networks (GANs)01:58:25
  • Week 9 – Practicum: (Energy-based) Generative adversarial networks01:15:12
  • Week 10 – Practicum: The Truck Backer-Upper01:00:26
  • Week 10 – Lecture: Self-supervised learning (SSL) in computer vision (CV)02:00:42
  • Week 11 – Practicum: Prediction and Policy learning Under Uncertainty (PPUU)01:23:19
  • Week 11 – Lecture: PyTorch activation and loss functions01:53:45
  • Week 12 – Practicum: Attention and the Transformer01:18:02
  • Week 12 – Lecture: Deep Learning for Natural Language Processing (NLP)01:40:57
  • Week 13 – Practicum: Graph Convolutional Neural Networks (GCN)01:10:02
  • Week 13 – Lecture: Graph Convolutional Networks (GCNs)02:00:23
  • Week 14 – Lecture: Structured prediction with energy based models02:07:31
  • Week 14 – Practicum: Overfitting and regularization, and Bayesian neural nets01:11:28
  • Week 15 – Practicum part A: Inference for latent variable energy based models (EBMs)59:05
  • Week 15 – Practicum part B: Training latent variable energy based models (EBMs)58:57
  • Matrix multiplication, signals, and convolutions47:02
  • Supervised and self-supervised transfer learning (with PyTorch Lightning)01:11:24
  • Four decades in Machine Learning: a Personal Journey by Yann LeCun01:31:23

You may also be interested in

FAQs

Suggest a Youtube Course

Our catalog is built based on the recommendations and interests of students like you.

Course Hive
Download now and unlock unlimited audiobooks — 100% free
Explore Now