Neural networks class

Hugo Larochelle, Université de Sherbrooke

These are the videos I use to teach my Neural networks class at Université de Sherbrooke

Neural networks [1.1] : Feedforward neural network - artificial neuron (7:51)

Neural networks [1.2] : Feedforward neural network - activation function (5:56)

Neural networks [1.3] : Feedforward neural network - capacity of single neuron (8:05)

Neural networks [1.4] : Feedforward neural network - multilayer neural network (13:11)

Neural networks [1.5] : Feedforward neural network - capacity of neural network (8:56)

Neural networks [1.6] : Feedforward neural network - biological inspiration (14:21)

Neural networks [2.1] : Training neural networks - empirical risk minimization (10:28)

Neural networks [2.2] : Training neural networks - loss function (4:49)

Neural networks [2.3] : Training neural networks - output layer gradient (12:03)

Neural networks [2.4] : Training neural networks - hidden layer gradient (15:15)

Neural networks [2.5] : Training neural networks - activation function derivative (4:37)

Neural networks [2.6] : Training neural networks - parameter gradient (6:26)

Neural networks [2.7] : Training neural networks - backpropagation (15:06)

Neural networks [2.8] : Training neural networks - regularization (13:15)

Neural networks [2.9] : Training neural networks - parameter initialization (6:10)

Neural networks [2.10] : Training neural networks - model selection (13:48)

Neural networks [2.11] : Training neural networks - optimization (23:40)

Neural networks [3.1] : Conditional random fields - motivation (5:19)

Neural networks [3.2] : Conditional random fields - linear chain CRF (9:58)

Neural networks [3.3] : Conditional random fields - context window (12:47)

Neural networks [3.4] : Conditional random fields - computing the partition function (24:34)

Neural networks [3.5] : Conditional random fields - computing marginals (9:08)

Neural networks [3.6] : Conditional random fields - performing classification (18:32)

Neural networks [3.7] : Conditional random fields - factors, sufficient statistics and linear CRF (11:37)

Neural networks [3.8] : Conditional random fields - Markov network (11:37)

Neural networks [3.9] : Conditional random fields - factor graph (6:28)

Neural networks [3.10] : Conditional random fields - belief propagation (24:48)

Neural networks [4.1] : Training CRFs - loss function (5:45)

Neural networks [4.2] : Training CRFs - unary log-factor gradient (13:29)

Neural networks [4.3] : Training CRFs - pairwise log-factor gradient (5:54)

Neural networks [4.4] : Training CRFs - discriminative vs. generative learning (6:44)

Neural networks [4.5] : Training CRFs - maximum-entropy Markov model (8:46)

Neural networks [4.6] : Training CRFs - hidden Markov model (4:17)

Neural networks [4.7] : Training CRFs - general conditional random field (6:30)

Neural networks [4.8] : Training CRFs - pseudolikelihood (5:11)

Neural networks [5.1] : Restricted Boltzmann machine - definition (12:17)

Neural networks [5.2] : Restricted Boltzmann machine - inference (18:32)

Neural networks [5.3] : Restricted Boltzmann machine - free energy (12:54)

Neural networks [5.4] : Restricted Boltzmann machine - contrastive divergence (13:34)

Neural networks [5.5] : Restricted Boltzmann machine - contrastive divergence (parameter update) (11:10)

Neural networks [5.6] : Restricted Boltzmann machine - persistent CD (7:36)

Neural networks [5.7] : Restricted Boltzmann machine - example (8:15)

Neural networks [5.8] : Restricted Boltzmann machine - extensions (9:19)

Neural networks [6.1] : Autoencoder - definition (6:15)

Neural networks [6.2] : Autoencoder - loss function (11:52)

Neural networks [6.3] : Autoencoder - example (2:54)

Neural networks [6.4] : Autoencoder - linear autoencoder (19:47)

Neural networks [6.5] : Autoencoder - undercomplete vs. overcomplete hidden layer (5:36)

Neural networks [6.6] : Autoencoder - denoising autoencoder (14:16)

Neural networks [6.7] : Autoencoder - contractive autoencoder (12:08)

Neural networks [7.1] : Deep learning - motivation (15:12)

Neural networks [7.2] : Deep learning - difficulty of training (8:24)

Neural networks [7.3] : Deep learning - unsupervised pre-training (12:52)

Neural networks [7.4] : Deep learning - example (12:41)

Neural networks [7.5] : Deep learning - dropout (11:18)

Neural networks [7.6] : Deep learning - deep autoencoder (7:34)

Neural networks [7.7] : Deep learning - deep belief network (13:22)

Neural networks [7.8] : Deep learning - variational bound (14:03)

Neural networks [7.9] : Deep learning - DBN pre-training (20:00)

Neural networks [8.1] : Sparse coding - definition (12:05)

Neural networks [8.2] : Sparse coding - inference (ISTA algorithm) (12:36)

Neural networks [8.3] : Sparse coding - dictionary update with projected gradient descent (5:04)

Neural networks [8.4] : Sparse coding - dictionary update with block-coordinate descent (13:10)

Neural networks [8.5] : Sparse coding - dictionary learning algorithm (5:31)

Neural networks [8.6] : Sparse coding - online dictionary learning algorithm (9:05)

Neural networks [8.7] : Sparse coding - ZCA preprocessing (8:39)

Neural networks [8.8] : Sparse coding - feature extraction (10:43)

Neural networks [8.9] : relationship with V1 (5:46)

Neural networks [9.1] : Computer vision - motivation (5:25)

Neural networks [9.2] : Computer vision - local connectivity (4:19)

Neural networks [9.3] : Computer vision - parameter sharing (11:32)

Neural networks [9.4] : Computer vision - discrete convolution (15:27)

Neural networks [9.5] : Computer vision - pooling and subsampling (8:11)

Neural networks [9.6] : Computer vision - convolutional network (13:58)

Neural networks [9.7] : Computer vision - object recognition (8:00)

Neural networks [9.8] : Computer vision - example (14:20)

Neural networks [9.9] : Computer vision - data set expansion (7:32)

Neural networks [9.10] : Computer vision - convolutional RBM (10:46)

Neural networks [10.1] : Natural language processing - motivation (2:16)

Neural networks [10.2] : Natural language processing - preprocessing (9:46)

Neural networks [10.3] : Natural language processing - one-hot encoding (7:31)

Neural networks [10.4] : Natural language processing - word representations (10:30)

Neural networks [10.5] : Natural language processing - language modeling (9:23)

Neural networks [10.6] : Natural language processing - neural network language model (16:08)

Neural networks [10.7] : Natural language processing - hierarchical output layer (13:51)

Neural networks [10.8] : Natural language processing - word tagging (10:48)

Neural networks [10.9] : Natural language processing - convolutional network (16:44)

Neural networks [10.10] : Natural language processing - multitask learning (16:03)

Neural networks [10.11] : Natural language processing - recursive network (5:50)

Neural networks [10.12] : Natural language processing - merging representations (3:40)

Neural networks [10.13] : Natural language processing - tree inference (16:51)

Neural networks [10.14] : Natural language processing - recursive network training (13:29)

Dates:
  • Free schedule
Course properties:
  • Free:
  • Paid:
  • Certificate:
  • MOOC:
  • Video:
  • Audio:
  • Email-course:
  • Language: English Gb

Reviews

No reviews yet. Want to be the first?

Register to leave a review

Show?id=n3eliycplgk&bids=695438
Included in selections:
Small-icon.hover Deep Learning
Good materials on deep learning.
NVIDIA
More on this topic:
65a295eb-3824-47e5-b6fe-ad881ef42c6b-460a74781a63.small Machine Learning-Based Predictive Modelling
Learn how to build predictive models using tree-based and other machine learning...
Logo_blue CSC321 Winter 2015: Introduction to Neural Networks
Machine learning is a powerful set of techniques that allow computers to learn...
Nvidia_logo Deep Learning for Image Classification with DIGITS
This course consists of 3 classes of 1 hour duration each and focuses on introducing...
Small-icon.hover Computational Neuroscience
Understanding how the brain works is one of the fundamental challenges in science...
Machinelearninglogo Machine Learning
Why write programs when the computer can instead learn them from data? In this...
More from 'Computer Science':
D8d3c316-0e41-4083-93ff-733a7e9b16bb-46a802220de9.small Capstone Exam in Statistics and Data Science
Solidify and demonstrate your knowledge and abilities in probability, data analysis...
Logo2 Network Science
The course is an interdisciplinary course, focused on the emerging science of...
3734fd64-86ca-48d2-96cd-68012918b899-a001bb3f9d3d.small Gameplay Programming for Video Game Designers
Learn how to create the best gameplay by understanding algorithmic thinking...
Regular_1bb827eb-8ea2-482a-af4a-fd767b047713 Introducing Robotics: Making Robots Move
The world needs people who understand how to get robots moving.
Regular_cce76e9c-434e-42e9-a6b1-e2d402812376 Python in High Performance Computing
Learn how to analyse Python programmes and identify performance barriers to...

© 2013-2019