Neural Networks for Machine Learning

1. 5 - 4 - Convolutional nets for object recognition [17min].mp423.03MB
2. 7 - 1 - Modeling sequences A brief overview.mp420.13MB
3. 14 - 1 - Learning layers of features by stacking RBMs [17 min].mp420.07MB
4. 14 - 5 - OPTIONAL VIDEO RBMs are infinite sigmoid belief nets [17 mins].mp419.44MB
5. 5 - 3 - Convolutional nets for digit recognition [16 min].mp418.46MB
6. 12 - 2 - OPTIONAL VIDEO More efficient ways to get the statistics [15 mins].mp416.93MB
7. 2 - 5 - What perceptrons cant do [15 min].mp416.57MB
8. 8 - 2 - Modeling character strings with multiplicative connections [14 mins].mp416.56MB
9. 8 - 1 - A brief overview of Hessian Free optimization.mp416.24MB
10. 16 - 3 - OPTIONAL Bayesian optimization of hyper-parameters [13 min].mp415.8MB
11. 13 - 4 - The wake-sleep algorithm [13 min].mp415.68MB
12. 10 - 1 - Why it helps to combine models [13 min].mp415.12MB
13. 6 - 5 - Rmsprop Divide the gradient by a running average of its recent magnitude.mp415.12MB
14. 1 - 1 - Why do we need machine learning [13 min].mp415.05MB
15. 10 - 2 - Mixtures of Experts [13 min].mp414.98MB
16. 6 - 2 - A bag of tricks for mini-batch gradient descent.mp414.9MB
17. 13 - 2 - Belief Nets [13 min].mp414.86MB
18. 11 - 1 - Hopfield Nets [13 min].mp414.65MB
19. 4 - 1 - Learning to predict the next word [13 min].mp414.28MB
20. 4 - 5 - Ways to deal with the large number of possible outputs [15 min].mp414.26MB
21. 12 - 1 - Boltzmann machine learning [12 min].mp414.03MB
22. 8 - 3 - Learning to predict the next character using HF [12 mins].mp413.92MB
23. 16 - 1 - OPTIONAL Learning a joint model of images and captions [10 min].mp413.83MB
24. 13 - 3 - Learning sigmoid belief nets [12 min].mp413.59MB
25. 9 - 1 - Overview of ways to improve generalization [12 min].mp413.57MB
26. 3 - 1 - Learning the weights of a linear neuron [12 min].mp413.52MB
27. 3 - 4 - The backpropagation algorithm [12 min].mp413.35MB
28. 11 - 5 - How a Boltzmann machine models data [12 min].mp413.28MB
29. 11 - 2 - Dealing with spurious minima [11 min].mp412.77MB
30. 12 - 3 - Restricted Boltzmann Machines [11 min].mp412.68MB
31. 9 - 5 - The Bayesian interpretation of weight decay [11 min].mp412.27MB
32. 9 - 4 - Introduction to the full Bayesian approach [12 min].mp412MB
33. 13 - 1 - The ups and downs of back propagation [10 min].mp411.83MB
34. 11 - 4 - Using stochastic units to improv search [11 min].mp411.76MB
35. 15 - 5 - Learning binary codes for image retrieval [9 mins].mp411.51MB
36. 11 - 3 - Hopfield nets with hidden units [10 min].mp411.31MB
37. 14 - 2 - Discriminative learning for DBNs [9 mins].mp411.29MB
38. 8 - 4 - Echo State Networks [9 min].mp411.28MB
39. 14 - 4 - Modeling real-valued data with an RBM [10 mins].mp411.2MB
40. 16 - 2 - OPTIONAL Hierarchical Coordinate Frames [10 mins].mp411.16MB
41. 3 - 5 - Using the derivatives computed by backpropagation [10 min].mp411.15MB
42. 15 - 3 - Deep auto encoders for document retrieval [8 mins].mp410.25MB
43. 7 - 5 - Long-term Short-term-memory.mp410.23MB
44. 14 - 3 - What happens during discriminative fine-tuning [8 mins].mp410.17MB
45. 15 - 4 - Semantic Hashing [9 mins].mp49.99MB
46. 1 - 2 - What are neural networks [8 min].mp49.76MB
47. 6 - 3 - The momentum method.mp49.74MB
48. 10 - 5 - Dropout [9 min].mp49.69MB
49. 15 - 1 - From PCA to autoencoders [5 mins].mp49.68MB
50. 6 - 1 - Overview of mini-batch gradient descent.mp49.6MB
51. 12 - 5 - RBMs for collaborative filtering [8 mins].mp49.53MB
52. 2 - 2 - Perceptrons The first generation of neural networks [8 min].mp49.39MB
53. 1 - 3 - Some simple models of neurons [8 min].mp49.26MB
54. 1 - 5 - Three types of learning [8 min].mp48.96MB
55. 4 - 4 - Neuro-probabilistic language models [8 min].mp48.93MB
56. 7 - 4 - Why it is difficult to train an RNN.mp48.89MB
57. 2 - 1 - Types of neural network architectures [7 min].mp48.78MB
58. 12 - 4 - An example of RBM learning [7 mins].mp48.71MB
59. 9 - 3 - Using noise as a regularizer [7 min].mp48.48MB
60. 10 - 3 - The idea of full Bayesian learning [7 min].mp48.39MB
61. 15 - 6 - Shallow autoencoders for pre-training [7 mins].mp48.25MB
62. 10 - 4 - Making full Bayesian learning practical [7 min].mp48.13MB
63. 4 - 3 - Another diversion The softmax output function [7 min].mp48.03MB
64. 9 - 2 - Limiting the size of the weights [6 min].mp47.36MB
65. 7 - 2 - Training RNNs with back propagation.mp47.33MB
66. 2 - 3 - A geometrical view of perceptrons [6 min].mp47.32MB
67. 7 - 3 - A toy example of training an RNN.mp47.24MB
68. 5 - 2 - Achieving viewpoint invariance [6 min].mp46.89MB
69. 6 - 4 - Adaptive learning rates for each connection.mp46.63MB
70. 1 - 4 - A simple example of learning [6 min].mp46.57MB
71. 2 - 4 - Why the learning works [5 min].mp45.9MB
72. 3 - 2 - The error surface for a linear neuron [5 min].mp45.89MB
73. 5 - 1 - Why object recognition is difficult [5 min].mp45.37MB
74. 4 - 2 - A brief diversion into cognitive science [4 min].mp45.31MB
75. 15 - 2 - Deep auto encoders [4 mins].mp44.92MB
76. 9 - 6 - MacKays quick and dirty method of setting weight costs [4 min].mp44.37MB
77. 3 - 3 - Learning the weights of a logistic output neuron [4 min].mp44.37MB
78. 16 - 4 - OPTIONAL The fog of progress [3 min].mp42.78MB