Coursera_Neural-Networks-and-Machine-Learning_Geoffrey-Hinton_University-of-Toronto

1. 1 - 1 - Why do we need machine learning [13 min].mp415.05MB
2. 1 - 2 - What are neural networks [8 min].mp49.76MB
3. 1 - 3 - Some simple models of neurons [8 min].mp49.26MB
4. 1 - 4 - A simple example of learning [6 min].mp46.57MB
5. 1 - 5 - Three types of learning [8 min].mp48.96MB
6. 10 - 1 - Why it helps to combine models [13 min].mp415.12MB
7. 10 - 2 - Mixtures of Experts [13 min].mp414.98MB
8. 10 - 3 - The idea of full Bayesian learning [7 min].mp48.39MB
9. 10 - 4 - Making full Bayesian learning practical [7 min].mp48.13MB
10. 10 - 5 - Dropout [9 min].mp49.69MB
11. 2 - 1 - Types of neural network architectures [7 min].mp48.78MB
12. 2 - 2 - Perceptrons The first generation of neural networks [8 min].mp49.39MB
13. 2 - 3 - A geometrical view of perceptrons [6 min].mp47.32MB
14. 2 - 4 - Why the learning works [5 min].mp45.9MB
15. 2 - 5 - What perceptrons cant do [15 min].mp416.57MB
16. 3 - 1 - Learning the weights of a linear neuron [12 min].mp413.52MB
17. 3 - 2 - The error surface for a linear neuron [5 min].mp45.89MB
18. 3 - 3 - Learning the weights of a logistic output neuron [4 min].mp44.37MB
19. 3 - 4 - The backpropagation algorithm [12 min].mp413.35MB
20. 3 - 5 - Using the derivatives computed by backpropagation [10 min].mp411.15MB
21. 4 - 1 - Learning to predict the next word [13 min].mp414.28MB
22. 4 - 2 - A brief diversion into cognitive science [4 min].mp45.31MB
23. 4 - 3 - Another diversion The softmax output function [7 min].mp48.03MB
24. 4 - 4 - Neuro-probabilistic language models [8 min].mp48.93MB
25. 4 - 5 - Ways to deal with the large number of possible outputs [15 min].mp414.26MB
26. 5 - 1 - Why object recognition is difficult [5 min].mp45.37MB
27. 5 - 2 - Achieving viewpoint invariance [6 min].mp46.89MB
28. 5 - 3 - Convolutional nets for digit recognition [16 min].mp418.46MB
29. 5 - 4 - Convolutional nets for object recognition [17min].mp423.03MB
30. 6 - 1 - Overview of mini-batch gradient descent.mp49.6MB
31. 6 - 2 - A bag of tricks for mini-batch gradient descent.mp414.9MB
32. 6 - 3 - The momentum method.mp49.74MB
33. 6 - 4 - Adaptive learning rates for each connection.mp46.63MB
34. 6 - 5 - Rmsprop Divide the gradient by a running average of its recent magnitude.mp415.12MB
35. 7 - 1 - Modeling sequences A brief overview.mp420.13MB
36. 7 - 2 - Training RNNs with back propagation.mp47.33MB
37. 7 - 3 - A toy example of training an RNN.mp47.24MB
38. 7 - 4 - Why it is difficult to train an RNN.mp48.89MB
39. 7 - 5 - Long-term Short-term-memory.mp410.23MB
40. 8 - 1 - A brief overview of Hessian Free optimization.mp416.24MB
41. 8 - 2 - Modeling character strings with multiplicative connections [14 mins].mp416.56MB
42. 8 - 3 - Learning to predict the next character using HF [12 mins].mp413.92MB
43. 8 - 4 - Echo State Networks [9 min].mp411.28MB
44. 9 - 1 - Overview of ways to improve generalization [12 min].mp413.57MB
45. 9 - 2 - Limiting the size of the weights [6 min].mp47.36MB
46. 9 - 3 - Using noise as a regularizer [7 min].mp48.48MB
47. 9 - 4 - Introduction to the full Bayesian approach [12 min].mp412MB
48. 9 - 5 - The Bayesian interpretation of weight decay [11 min].mp412.27MB
49. 9 - 6 - MacKays quick and dirty method of setting weight costs [4 min].mp44.37MB