30 Days
Classroom / Online
Tools Covered
R Programming Language, Python, Jupyter, Keras, H2o, IBM Watson
Pre-requisites
What you will learn
Part 1 – Artificial Neural Networks
All below sections will be implemented with tensorflow and keras, Programming knowledge of tensorflow and keras will be given during model buildings.
Section 1
1. Artificial Neural networks Intuition
2. Plan of Attack
3. The Neuron
4. The Activation Function
5. How do Neural Networks work?
6. How do Neural Networks learn?
7. Gradient Descent
8. Stochastic Gradient Descent
9. Backpropagation
Section 2
10. Building an ANN
11. Prerequisites
12. How to get the dataset
13. Business Problem Description
14. Building an ANN – Step 1
15. Building an ANN – Step 2
16. Building an ANN – Step 3
17. Building an ANN – Step 4
18. Building an ANN – Step 5
19. Building an ANN – Step 6
20. Building an ANN – Step 7
21. Building an ANN – Step 8
22. Building an ANN – Step 9
23. Building an ANN – Step 10
Section 3
24. Homework Challenge – Should we say goodbye to that customer?
25. Homework Instruction
26. Homework Solution
Section 4
27. Evaluating, Improving and Tuning the ANN
28. Evaluating the ANN
29. Improving the ANN
30. Tuning the ANN
Part 2 – Convolutional Neural Networks
Section 5
31. CNN Intuition
32. What you’ll Need for CNN
33. Plan of attack
34. What are convolutional neural networks?
35. Step 1 – Convolution Operation
36. Step 1(b) – ReLU Layer
37. Step 2 – Pooling
38. Step 3 – Flattening
39. Step 4 – Full Connection
40. Summary
41. Softmax
42. Cross-Entropy
Section 6
43. Building a CNN
44. How to get the dataset
45. Introduction to CNNs
46. Building a CNN – Step 1
47. Building a CNN – Step 2
48. Building a CNN – Step 3
49. Building a CNN – Step 4
50. Building a CNN – Step 5
51. Building a CNN – Step 6
52. Building a CNN – Step 7
53. Building a CNN – Step 8
54. Building a CNN – Step 9
55. Building a CNN – Step 10
Section 7
56. Homework – What’s that pet?
57. Homework Instruction
58. Homework Solution
59. Evaluating, Improving and Tuning the CNN
Part 3 – Recurrent Neural Networks
Section 8
60. RNN (Recurrent Neural networks) Intuition
61. What you’ll need for RNN
62. Plan of attack
63. The idea behind Recurrent Neural Networks
64. The Vanishing Gradient Problem
65. LSTMs
66. Practical intuition
67. LSTM Variations
Section 9
68. Building a RNN
69. How to get the dataset
70. Building a RNN – Step 1
71. Building a RNN – Step 2
72. Building a RNN – Step 3
73. Building a RNN – Step 4
74. Building a RNN – Step 5
75. Building a RNN – Step 6
76. Building a RNN – Step 7
77. Building a RNN – Step 8
78. Building a RNN – Step 9
79. Building a RNN – Step 10
80. Building a RNN – Step 11
81. Building a RNN – Step 12
82. Building a RNN – Step 13
83. Building a RNN – Step 14
84. Building a RNN – Step 15
Section 10
85. Evaluating, Improving and Tuning the RNN
86. Evaluating the RNN
87. Improving the RNN
88. Tuning the RNN
Part 4 – Self Organizing Maps
Section 11
89. SOMs [Self-Organizing Maps] Intuition
90. Plan of attack
91. How do Self-Organizing Maps Work?
92. Why revisit K-Means?
93. K-Means Clustering (Refresher)
94. How do Self-Organizing Maps Learn? (Part 1)
95. How do Self-Organizing Maps Learn? (Part 2)
96. Live SOM example
97. Reading an Advanced SOM
98. K-means Clustering (part 2)
99. K-means Clustering (part 3)
Section 12
100. Building a SOM
101. How to get the dataset
103. Building a SOM – Step 1
104. Building a SOM – Step 2
105. Building a SOM – Step 3
106. Building a SOM – Step 4
Section 13
Case study All above sections will be implemented with tensorflow and keras, Programming knowledge of tensorflow and keras will be given during Model buildings
Course | Date | Timings | Duration | Trainer | Location |