Coursera - Neural Networks and Machine Learning, Geoffrey Hinton University of Toronto

1. 5 - 4 - Convolutional nets for object recognition [17min].mp423.03 MB
2. 7 - 1 - Modeling sequences A brief overview.mp420.13 MB
3. 5 - 3 - Convolutional nets for digit recognition [16 min].mp418.46 MB
4. 2 - 5 - What perceptrons cant do [15 min].mp416.57 MB
5. 8 - 2 - Modeling character strings with multiplicative connections [14 mins].mp416.56 MB
6. 8 - 1 - A brief overview of Hessian Free optimization.mp416.24 MB
7. 10 - 1 - Why it helps to combine models [13 min].mp415.12 MB
8. 6 - 5 - Rmsprop Divide the gradient by a running average of its recent magnitude.mp415.12 MB
9. 1 - 1 - Why do we need machine learning [13 min].mp415.05 MB
10. 10 - 2 - Mixtures of Experts [13 min].mp414.98 MB
11. 6 - 2 - A bag of tricks for mini-batch gradient descent.mp414.9 MB
12. 4 - 1 - Learning to predict the next word [13 min].mp414.28 MB
13. 4 - 5 - Ways to deal with the large number of possible outputs [15 min].mp414.26 MB
14. 8 - 3 - Learning to predict the next character using HF [12 mins].mp413.92 MB
15. 9 - 1 - Overview of ways to improve generalization [12 min].mp413.57 MB
16. 3 - 1 - Learning the weights of a linear neuron [12 min].mp413.52 MB
17. 3 - 4 - The backpropagation algorithm [12 min].mp413.35 MB
18. 9 - 5 - The Bayesian interpretation of weight decay [11 min].mp412.27 MB
19. 9 - 4 - Introduction to the full Bayesian approach [12 min].mp412 MB
20. 8 - 4 - Echo State Networks [9 min].mp411.28 MB
21. 3 - 5 - Using the derivatives computed by backpropagation [10 min].mp411.15 MB
22. 7 - 5 - Long-term Short-term-memory.mp410.23 MB
23. 1 - 2 - What are neural networks [8 min].mp49.76 MB
24. 6 - 3 - The momentum method.mp49.74 MB
25. 10 - 5 - Dropout [9 min].mp49.69 MB
26. 6 - 1 - Overview of mini-batch gradient descent.mp49.6 MB
27. 2 - 2 - Perceptrons The first generation of neural networks [8 min].mp49.39 MB
28. 1 - 3 - Some simple models of neurons [8 min].mp49.26 MB
29. 1 - 5 - Three types of learning [8 min].mp48.96 MB
30. 4 - 4 - Neuro-probabilistic language models [8 min].mp48.93 MB
31. 7 - 4 - Why it is difficult to train an RNN.mp48.89 MB
32. 2 - 1 - Types of neural network architectures [7 min].mp48.78 MB
33. 9 - 3 - Using noise as a regularizer [7 min].mp48.48 MB
34. 10 - 3 - The idea of full Bayesian learning [7 min].mp48.39 MB
35. 10 - 4 - Making full Bayesian learning practical [7 min].mp48.13 MB
36. 4 - 3 - Another diversion The softmax output function [7 min].mp48.03 MB
37. 9 - 2 - Limiting the size of the weights [6 min].mp47.36 MB
38. 7 - 2 - Training RNNs with back propagation.mp47.33 MB
39. 2 - 3 - A geometrical view of perceptrons [6 min].mp47.32 MB
40. 7 - 3 - A toy example of training an RNN.mp47.24 MB
41. 5 - 2 - Achieving viewpoint invariance [6 min].mp46.89 MB
42. 6 - 4 - Adaptive learning rates for each connection.mp46.63 MB
43. 1 - 4 - A simple example of learning [6 min].mp46.57 MB
44. 2 - 4 - Why the learning works [5 min].mp45.9 MB
45. 3 - 2 - The error surface for a linear neuron [5 min].mp45.89 MB
46. 5 - 1 - Why object recognition is difficult [5 min].mp45.37 MB
47. 4 - 2 - A brief diversion into cognitive science [4 min].mp45.31 MB
48. 9 - 6 - MacKays quick and dirty method of setting weight costs [4 min].mp44.37 MB
49. 3 - 3 - Learning the weights of a logistic output neuron [4 min].mp44.37 MB