**The Complete Self-Driving Car Course – Applied Deep Learning**

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 18 Hours | 9.22 GB

eLearning | Skill level: All Levels

Learn to use Deep Learning, Computer Vision and Machine Learning techniques to Build an Autonomous Car with Python

Self-driving cars, have rapidly become one of the most transformative technologies to emerge. Fuelled by Deep Learning algorithms, they are continuously driving our society forward, and creating new opportunities in the mobility sector.

Deep Learning jobs command some of the highest salaries in the development world. This is the first, and only course which makes practical use of Deep Learning, and applies it to building a self-driving car, one of the most disruptive technologies in the world today.

Learn & Master Deep Learning in this fun and exciting course with top instructor Rayan Slim. With over 28000 students, Rayan is a highly rated and experienced instructor who has followed a “learn by doing” style to create this amazing course.

You’ll go from beginner to Deep Learning expert and your instructor will complete each task with you step by step on screen.

By the end of the course, you will have built a fully functional self-driving car fuelled entirely by Deep Learning. This powerful simulation will impress even the most senior developers and ensure you have hands on skills in neural networks that you can bring to any project or company.

This course will show you how to:

- Use Computer Vision techniques via OpenCV to identify lane lines for a self-driving car.
- Learn to train a Perceptron-based Neural Network to classify between binary classes.
- Learn to train Convolutional Neural Networks to identify between various traffic signs.
- Train Deep Neural Networks to fit complex datasets.
- Master Keras, a power Neural Network library written in Python.
- Build and train a fully functional self driving car to drive on its own!

No experience required. This course is designed to take students with no programming/mathematics experience to accomplished Deep Learning developers.

This course also comes with all the source code and friendly support in the Q&A area.

What you’ll learn

- Learn to apply Computer Vision and Deep Learning techniques to build automotive-related algorithms
- Understand, build and train Convolutional Neural Networks with Keras
- Simulate a fully functional Self-Driving Car with Convolutional Neural Networks and Computer Vision
- Train a Deep Learning Model that can identify between 43 different Traffic Signs
- Learn to use essential Computer Vision techniques to identify lane lines on a road
- Learn to build and train powerful Neural Networks with Keras
- Understand Neural Networks at the most fundamental perceptron-based level

**+ Table of Contents**

**Introduction**

1 Why This Course

**Installation**

2 Overview

3 Anaconda Distribution – Mac

4 Anaconda Distribution – Windows

5 Text Editor

6 Outro

**Python Crash Course (Optional)**

7 Python Crash Course Part 1 – Data Types

8 Slicing

9 Membership Operators

10 Mutability

11 Mutability II

12 Common Functions & Methods

13 Tuples

14 Sets

15 Dictionaries

16 Compound Data Structures

17 Part 1 – Outro

18 Jupyter Notebooks

19 Part 2 – Control Flow

20 If, else

21 elif

22 Complex Comparisons

23 For Loops

24 For Loops II

25 While Loops

26 Break

27 Part 2 – Outro

28 Part 3 – Functions

29 Arithmetic Operations

30 Functions

31 Scope

32 Doc Strings

33 Lambda & Higher Order Functions

34 Part 3 – Outro

35 Variables

36 Numeric Data Types

37 String Data Types

38 Booleans

39 Methods

40 Lists

**NumPy Crash Course (Optional)**

41 Overview

42 Part 4 – Outro

43 Vector Addition – Arrays vs Lists

44 Multidimensional Arrays

45 One Dimensional Slicing

46 Reshaping

47 Multidimensional Slicing

48 Manipulating Array Shapes

49 Matrix Multiplication

50 Stacking

**Computer Vision Finding Lane Lines**

51 Overview

52 Hough Transform II

53 Optimizing

54 Resource for upcoming video

55 Finding Lanes on Video

56 Source Code

57 Part 5 – Conclusion

58 Image needed for the next lesson

59 Loading Image

60 Grayscale Conversion

61 Smoothening Image

62 Simple Edge Detection

63 Region of Interest

64 Binary Numbers & Bitwise and

65 Line Detection – Hough Transform

**The Perceptron**

66 Overview

67 Error Function

68 Sigmoid

69 Sigmoid Implementation (Code)

70 Source code

71 Cross Entropy

72 Cross Entropy (Code)

73 Source Code

74 Gradient Descent

75 Gradient Descent (Code)

76 Recap

77 Machine Learning

78 Source Code

79 Part 6 – Conclusion

80 Supervised Learning – Friendly Example

81 Classification

82 Linear Model

83 Perceptrons

84 Weights

85 Project – Initial Stages

86 Sample Code for Initial Stages

**Keras**

87 Overview

88 Intro to Keras

89 Starter Code

90 Keras Models

91 Keras – Predictions

92 Source Code

93 Part 7 – Outro

**Deep Neural Networks**

94 Overview

95 Non-Linear Boundaries

96 Architecture

97 Feedforward Process

98 Error Function

99 Backpropagation

100 Code Implementation

101 Source Code

102 Section 8 – Conclusion

**Multiclass Classification**

103 Overview

104 Softmax

105 Cross Entropy

106 Implementation

107 Source Code

108 Section 9 – Outro

**MNIST Image Recognition**

109 Overview

110 Section 10 – Outro

111 MNIST Dataset

112 Train & Test

113 Hyperparameters

114 Implementation Part 1

115 Implementation Part 2

116 Resource for upcoming video

117 Implementation Part 3

118 Final Source Code

**Convolutional Neural Networks**

119 Overview

120 Final Source Code

121 Section 11 – Conclusion

122 Convolutions & MNIST

123 Convolutional Layer

124 Convolutions II

125 Pooling

126 Fully Connected Layer

127 Starter Code

128 Code Implementation I

129 Code Implementation II

**Classifying Road Symbols**

130 Overview

131 Section 12 – Outro

132 Traffic Signs Starter Code

133 Preprocessing Images

134 leNet Implementation

135 Fine-tuning Model

136 Resources Needed for Testing

137 Testing

138 Fit Generator

139 Final Source Code

**Polynomial Regression**

140 Overview

141 Implementation

142 Final Source Code

143 Section 13 – Conclusion

**Behavioural Cloning**

144 Overview

145 Collecting Data

146 Downloading Data

147 Balancing Data

148 Training & Validation Split

149 Preprocessing Images

150 Defining Nvidia Model

151 Drive.py code

152 Flask & Socket.io

153 Self Driving Car – Test 1

154 Generator – Augmentation Techniques

155 Batch Generator

156 Fit Generator

157 Final Source Code

158 Outro