English | 2016 | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 9 Hours | 1.74 GB
A comprehensive introduction to Deep Learning with Python.
Get ready to train your machine learning algorithms. Starting off with core Python coverage and swiftly moving to practical deep learning content, this Learning Path will have you crunching stats and quoting facts in no time at all.
This path navigates across the following products (in sequential order):
- Beginning Python (4h 20m)
- Mastering Python (2h 35m)
- Deep Learning with Python (1h 45m)
Table of Contents
Beginning Python
1. The Course Overview and Installing Python
2. Setting Up a Programming Environment
3. Variables
4. Introduction to Types
5. Basic Operators
6. Introduction to Strings
7. String Functions
8. Advanced String Manipulation
9. String Formatting
10. User Input
11. Introduction to Lists
12. List Methods
13. Advanced List Methods
14. Built-in List Functions
15. 2D Arrays and Array References
16. List Slicing
17. Conditionals
18. Comparison Operators
19. Else and Elif
20. and, or, and not
21. Conditional Examples
22. Mini Program
23. For Loop
24. While Loop
25. Iterables
26. Loops and Conditionals
27. Prime Number Checker
28. Function Basics
29. Parameters and Arguments
30. Return versus Void Functions
31. Working with Examples
32. Advanced Examples
33. Recursion
34. Recursion Examples
35. Import, as, and from
36. Python API and Modules
37. Creating Modules
38. Modules and Testing
39. Installing PIL-Pillow
40. Basics of Using PIL-Pillow
41. Picture Manipulations
42. Custom Picture Manipulation
43. Wrapping Up
Mastering Python
44. Downloading and Installing Python
45. Using the Command Line and the Interactive Shell
46. Installing Packages with pip
47. Finding Packages in the Python Package Index
48. Creating an Empty Package
49. Adding Modules to the Package
50. Importing One of the Package-s Modules from Another
51. Adding Data Files to the Package
52. PEP 8 and Writing Readable Code
53. Using Version Control
54. Using venv to Create a Stable and Isolated Work Area
55. Getting the Most Out of docstrings Part 1 – PEP 257 and Sphinx
56. Getting the Most Out of docstrings Part 2 – doctest
57. Making a Package Executable via python – m
58. Handling Command-line Arguments with argparse
59. Text-mode Interactivity
60. Executing Other Programs
61. Using Shell Scripts or Batch Files to Launch Programs
62. Using concurrent.futures
63. Using Multiprocessing
64. Understanding Why Asynchronous I-O Isn-t Like Parallel Processing
65. Using the asyncio Event Loop and Coroutine Scheduler
66. Futures
67. Making Asynchronous Tasks Interoperate
68. Communicating across the Network
69. Using Function Decorators
70. Using Function Annotations
71. Using Class Decorators
72. Using Metaclasses
73. Using Context Managers
74. Using Descriptors
75. Understanding the Principles of Unit Testing
76. Using unittest
77. Using unittest.mock
78. Using unittest-s Test Discovery
79. Using Nose for Unified Test Discovery and Reporting
Deep Learning with Python
80. The Course Overview
81. What Is Deep Learning
82. Open Source Libraries for Deep Learning
83. Deep Learning Hello World Classifying the MNIST Data
84. Introduction to Backpropagation
85. Understanding Deep Learning with Theano
86. Optimizing a Simple Model in Pure Theano
87. Keras Behind the Scenes
88. Fully Connected or Dense Layers
89. Convolutional and Pooling Layers
90. Large Scale Datasets, ImageNet, and Very Deep Neural Networks
91. Loading Pre-trained Models with Theano
92. Reusing Pre-trained Models in New Applications
93. Theano for Loops – the scan Module
94. Recurrent Layers
95. Recurrent Versus Convolutional Layers
96. Recurrent Networks –Training a Sentiment Analysis Model for Text
97. Bonus Challenge – Automatic Image Captioning
98. Captioning TensorFlow – Google-s Machine Learning Library
part 1 files 1-22
part 2 files 23-46
part 3 files 47-87
part 4 files 88-98
Resolve the captcha to access the links!