Filename Size 1 - 1 - Why do we need machine learning [13 min].mp4 15 MB 1 - 2 - What are neural networks [8 min].mp4 9.8 MB 1 - 3 - Some simple models of neurons [8 min].mp4 9.3 MB 1 - 4 - A simple example of learning [6 min].mp4 6.6 MB 1 - 5 - Three types of learning [8 min].mp4 9 MB 10 - 1 - Why it helps to combine models [13 min].mp4 15.1 MB 10 - 2 - Mixtures of Experts [13 min].mp4 15 MB 10 - 3 - The idea of full Bayesian learning [7 min].mp4 8.4 MB 10 - 4 - Making full Bayesian learning practical [7 min].mp4 8.1 MB 10 - 5 - Dropout [9 min].mp4 9.7 MB 2 - 1 - Types of neural network architectures [7 min].mp4 8.8 MB 2 - 2 - Perceptrons The first generation of neural networks [8 min].mp4 9.4 MB 2 - 3 - A geometrical view of perceptrons [6 min].mp4 7.3 MB 2 - 4 - Why the learning works [5 min].mp4 5.9 MB 2 - 5 - What perceptrons cant do [15 min].mp4 16.6 MB 3 - 1 - Learning the weights of a linear neuron [12 min].mp4 13.5 MB 3 - 2 - The error surface for a linear neuron [5 min].mp4 5.9 MB 3 - 3 - Learning the weights of a logistic output neuron [4 min].mp4 4.4 MB 3 - 4 - The backpropagation algorithm [12 min].mp4 13.4 MB 3 - 5 - Using the derivatives computed by backpropagation [10 min].mp4 11.2 MB 4 - 1 - Learning to predict the next word [13 min].mp4 14.3 MB 4 - 2 - A brief diversion into cognitive science [4 min].mp4 5.3 MB 4 - 3 - Another diversion The softmax output function [7 min].mp4 8 MB 4 - 4 - Neuro-probabilistic language models [8 min].mp4 8.9 MB 4 - 5 - Ways to deal with the large number of possible outputs [15 min].mp4 14.3 MB 5 - 1 - Why object recognition is difficult [5 min].mp4 5.4 MB 5 - 2 - Achieving viewpoint invariance [6 min].mp4 6.9 MB 5 - 3 - Convolutional nets for digit recognition [16 min].mp4 18.5 MB 5 - 4 - Convolutional nets for object recognition [17min].mp4 23 MB 6 - 1 - Overview of mini-batch gradient descent.mp4 9.6 MB 6 - 2 - A bag of tricks for mini-batch gradient descent.mp4 14.9 MB 6 - 3 - The momentum method.mp4 9.7 MB 6 - 4 - Adaptive learning rates for each connection.mp4 6.6 MB 6 - 5 - Rmsprop Divide the gradient by a running average of its recent magnitude.mp4 15.1 MB 7 - 1 - Modeling sequences A brief overview.mp4 20.1 MB 7 - 2 - Training RNNs with back propagation.mp4 7.3 MB 7 - 3 - A toy example of training an RNN.mp4 7.2 MB 7 - 4 - Why it is difficult to train an RNN.mp4 8.9 MB 7 - 5 - Long-term Short-term-memory.mp4 10.2 MB 8 - 1 - A brief overview of Hessian Free optimization.mp4 16.2 MB 8 - 2 - Modeling character strings with multiplicative connections [14 mins].mp4 16.6 MB 8 - 3 - Learning to predict the next character using HF [12 mins].mp4 13.9 MB 8 - 4 - Echo State Networks [9 min].mp4 11.3 MB 9 - 1 - Overview of ways to improve generalization [12 min].mp4 13.6 MB 9 - 2 - Limiting the size of the weights [6 min].mp4 7.4 MB 9 - 3 - Using noise as a regularizer [7 min].mp4 8.5 MB 9 - 4 - Introduction to the full Bayesian approach [12 min].mp4 12 MB 9 - 5 - The Bayesian interpretation of weight decay [11 min].mp4 12.3 MB 9 - 6 - MacKays quick and dirty method of setting weight costs [4 min].mp4 4.4 MB
No related downloads found.
