Neural Networks for Machine Learning

1. 0101 Why do we need machine learning_.mp415.05MB
2. 0102 What are neural networks_.mp49.76MB
3. 0103 Some simple models of neurons.mp49.26MB
4. 0104 A simple example of learning.mp46.57MB
5. 0105 Three types of learning.mp48.96MB
6. 0201 Types of neural network architectures.mp48.78MB
7. 0202 Perceptrons_ The first generation of neural networks.mp49.78MB
8. 0203 A geometrical view of perceptrons.mp47.32MB
9. 0204 Why the learning works.mp45.9MB
10. 0205 What perceptrons can_t do.mp416.57MB
11. 0301 Learning the weights of a linear neuron.mp413.52MB
12. 0302 The error surface for a linear neuron.mp45.89MB
13. 0303 Learning the weights of a logistic output neuron.mp44.37MB
14. 0304 The backpropagation algorithm.mp413.35MB
15. 0305 Using the derivatives computed by backpropagation.mp411.15MB
16. 0401 Learning to predict the next word.mp414.28MB
17. 0402 A brief diversion into cognitive science.mp45.31MB
18. 0403 Another diversion_ The softmax output function.mp48.03MB
19. 0404 Neuro-probabilistic language models.mp48.93MB
20. 0405 Ways to deal with the large number of possible outputs.mp414.26MB
21. 0501 Why object recognition is difficult.mp45.37MB
22. 0502 Achieving viewpoint invariance.mp46.89MB
23. 0503 Convolutional nets for digit recognition.mp418.46MB
24. 0504 Convolutional nets for object recognition.mp423.03MB
25. 0601 Overview of mini-batch gradient descent.mp49.6MB
26. 0602 A bag of tricks for mini-batch gradient descent.mp414.9MB
27. 0603 The momentum method.mp49.74MB
28. 0604 Adaptive learning rates for each connection.mp46.63MB
29. 0605 Rmsprop_ Divide the gradient by a running average of its recent magnitude.mp415.12MB
30. 0701 Modeling sequences_ A brief overview.mp420.13MB
31. 0702 Training RNNs with back propagation.mp47.33MB
32. 0703 A toy example of training an RNN.mp47.24MB
33. 0704 Why it is difficult to train an RNN.mp48.89MB
34. 0705 Long-term Short-term-memory.mp410.23MB
35. 0801 A brief overview of Hessian Free optimization.mp416.24MB
36. 0802 Modeling character strings with multiplicative connections.mp416.56MB
37. 0803 Learning to predict the next character using HF.mp413.92MB
38. 0804 Echo State Networks.mp411.28MB
39. 0901 Overview of ways to improve generalization.mp413.57MB
40. 0902 Limiting the size of the weights.mp47.36MB
41. 0903 Using noise as a regularizer.mp48.48MB
42. 0904 Introduction to the full Bayesian approach.mp412MB
43. 0905 The Bayesian interpretation of weight decay.mp412.27MB
44. 0906 MacKay_s quick and dirty method of setting weight costs.mp44.37MB
45. 1001 Why it helps to combine models.mp415.12MB
46. 1002 Mixtures of Experts.mp414.98MB
47. 1003 The idea of full Bayesian learning.mp48.39MB
48. 1004 Making full Bayesian learning practical.mp48.13MB
49. 1005 Dropout.mp49.69MB
50. 1101 Hopfield Nets.mp414.65MB
51. 1102 Dealing with spurious minima.mp412.77MB
52. 1103 Hopfield nets with hidden units.mp411.31MB
53. 1104 Using stochastic units to improv search.mp411.76MB
54. 1105 How a Boltzmann machine models data.mp413.28MB
55. 1201 Boltzmann machine learning.mp414.03MB
56. 1202 OPTIONAL VIDEO_ More efficient ways to get the statistics.mp416.93MB
57. 1203 Restricted Boltzmann Machines.mp412.68MB
58. 1204 An example of RBM learning.mp48.71MB
59. 1205 RBMs for collaborative filtering.mp49.53MB
60. 1301 The ups and downs of back propagation.mp411.83MB
61. 1302 Belief Nets.mp414.86MB
62. 1303 Learning sigmoid belief nets.mp414.19MB
63. 1304 The wake-sleep algorithm.mp415.68MB
64. 1401 Learning layers of features by stacking RBMs.mp420.07MB
65. 1402 Discriminative learning for DBNs.mp411.29MB
66. 1403 What happens during discriminative fine-tuning_.mp410.17MB
67. 1404 Modeling real-valued data with an RBM.mp411.2MB
68. 1405 OPTIONAL VIDEO_ RBMs are infinite sigmoid belief nets.mp419.44MB
69. 1501 From PCA to autoencoders.mp49.68MB
70. 1502 Deep auto encoders.mp44.92MB
71. 1503 Deep auto encoders for document retrieval.mp410.25MB
72. 1504 Semantic Hashing.mp410.97MB
73. 1505 Learning binary codes for image retrieval.mp411.51MB
74. 1506 Shallow autoencoders for pre-training.mp48.25MB
75. 1601 OPTIONAL_ Learning a joint model of images and captions.mp413.83MB
76. 1602 OPTIONAL_ Hierarchical Coordinate Frames.mp411.16MB
77. 1603 OPTIONAL_ Bayesian optimization of hyper-parameters.mp415.8MB
78. 1604 OPTIONAL_ The fog of progress.mp42.78MB