|
Please note that this page does not hosts or makes available any of the listed filenames. You
cannot download any of those files from here.
|
| 10 - 1 - Why it helps to combine models [13 min].mp4 |
15.12MB |
| 10 - 2 - Mixtures of Experts [13 min].mp4 |
14.98MB |
| 10 - 3 - The idea of full Bayesian learning [7 min].mp4 |
8.39MB |
| 10 - 4 - Making full Bayesian learning practical [7 min].mp4 |
8.13MB |
| 10 - 5 - Dropout [9 min].mp4 |
9.69MB |
| 1 - 1 - Why do we need machine learning [13 min].mp4 |
15.05MB |
| 1 - 2 - What are neural networks [8 min].mp4 |
9.76MB |
| 1 - 3 - Some simple models of neurons [8 min].mp4 |
9.26MB |
| 1 - 4 - A simple example of learning [6 min].mp4 |
6.57MB |
| 1 - 5 - Three types of learning [8 min].mp4 |
8.96MB |
| 2 - 1 - Types of neural network architectures [7 min].mp4 |
8.78MB |
| 2 - 2 - Perceptrons The first generation of neural networks [8 min].mp4 |
9.39MB |
| 2 - 3 - A geometrical view of perceptrons [6 min].mp4 |
7.32MB |
| 2 - 4 - Why the learning works [5 min].mp4 |
5.90MB |
| 2 - 5 - What perceptrons cant do [15 min].mp4 |
16.57MB |
| 3 - 1 - Learning the weights of a linear neuron [12 min].mp4 |
13.52MB |
| 3 - 2 - The error surface for a linear neuron [5 min].mp4 |
5.89MB |
| 3 - 3 - Learning the weights of a logistic output neuron [4 min].mp4 |
4.37MB |
| 3 - 4 - The backpropagation algorithm [12 min].mp4 |
13.35MB |
| 3 - 5 - Using the derivatives computed by backpropagation [10 min].mp4 |
11.15MB |
| 4 - 1 - Learning to predict the next word [13 min].mp4 |
14.28MB |
| 4 - 2 - A brief diversion into cognitive science [4 min].mp4 |
5.31MB |
| 4 - 3 - Another diversion The softmax output function [7 min].mp4 |
8.03MB |
| 4 - 4 - Neuro-probabilistic language models [8 min].mp4 |
8.93MB |
| 4 - 5 - Ways to deal with the large number of possible outputs [15 min].mp4 |
14.26MB |
| 5 - 1 - Why object recognition is difficult [5 min].mp4 |
5.37MB |
| 5 - 2 - Achieving viewpoint invariance [6 min].mp4 |
6.89MB |
| 5 - 3 - Convolutional nets for digit recognition [16 min].mp4 |
18.46MB |
| 5 - 4 - Convolutional nets for object recognition [17min].mp4 |
23.03MB |
| 6 - 1 - Overview of mini-batch gradient descent.mp4 |
9.60MB |
| 6 - 2 - A bag of tricks for mini-batch gradient descent.mp4 |
14.90MB |
| 6 - 3 - The momentum method.mp4 |
9.74MB |
| 6 - 4 - Adaptive learning rates for each connection.mp4 |
6.63MB |
| 6 - 5 - Rmsprop Divide the gradient by a running average of its recent magnitude.mp4 |
15.12MB |
| 7 - 1 - Modeling sequences A brief overview.mp4 |
20.13MB |
| 7 - 2 - Training RNNs with back propagation.mp4 |
7.33MB |
| 7 - 3 - A toy example of training an RNN.mp4 |
7.24MB |
| 7 - 4 - Why it is difficult to train an RNN.mp4 |
8.89MB |
| 7 - 5 - Long-term Short-term-memory.mp4 |
10.23MB |
| 8 - 1 - A brief overview of Hessian Free optimization.mp4 |
16.24MB |
| 8 - 2 - Modeling character strings with multiplicative connections [14 mins].mp4 |
16.56MB |
| 8 - 3 - Learning to predict the next character using HF [12 mins].mp4 |
13.92MB |
| 8 - 4 - Echo State Networks [9 min].mp4 |
11.28MB |
| 9 - 1 - Overview of ways to improve generalization [12 min].mp4 |
13.57MB |
| 9 - 2 - Limiting the size of the weights [6 min].mp4 |
7.36MB |
| 9 - 3 - Using noise as a regularizer [7 min].mp4 |
8.48MB |
| 9 - 4 - Introduction to the full Bayesian approach [12 min].mp4 |
12.00MB |
| 9 - 5 - The Bayesian interpretation of weight decay [11 min].mp4 |
12.27MB |
| 9 - 6 - MacKays quick and dirty method of setting weight costs [4 min].mp4 |
4.37MB |