**Zero to Deep Learning™ with Python and Keras**

English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 10 Hours | 1.83 GB

eLearning | Skill level: All Levels

Understand and build Deep Learning models for images, text and more using Python and Keras

This course is designed to provide a complete introduction to Deep Learning. It is aimed at beginners and intermediate programmers and data scientists who are familiar with Python and want to understand and apply Deep Learning techniques to a variety of problems.

We start with a review of Deep Learning applications and a recap of Machine Learning tools and techniques. Then we introduce Artificial Neural Networks and explain how they are trained to solve Regression and Classification problems.

Over the rest of the course we introduce and explain several architectures including Fully Connected, Convolutional and Recurrent Neural Networks, and for each of these we explain both the theory and give plenty of example applications.

This course is a good balance between theory and practice. We don’t shy away from explaining mathematical details and at the same time we provide exercises and sample code to apply what you’ve just learned.

The goal is to provide students with a strong foundation, not just theory, not just scripting, but both. At the end of the course you’ll be able to recognize which problems can be solved with Deep Learning, you’ll be able to design and train a variety of Neural Network models and you’ll be able to use cloud computing to speed up training and improve your model’s performance.

What you’ll learn

- To describe what Deep Learning is in a simple yet accurate way
- To explain how deep learning can be used to build predictive models
- To distinguish which practical applications can benefit from deep learning
- To install and use Python and Keras to build deep learning models
- To apply deep learning to solve supervised and unsupervised learning problems involving images, text, sound, time series and tabular data.
- To build, train and use fully connected, convolutional and recurrent neural networks
- To look at the internals of a deep learning model without intimidation and with the ability to tweak its parameters
- To train and run models in the cloud using a GPU
- To estimate training costs for large models
- To re-use pre-trained models to shortcut training time and cost (transfer learning)

**+ Table of Contents**

**Welcome to the course!**

1 Welcome to the course!

2 Introduction

3 Real world applications of deep learning

4 Download and install Anaconda

5 Installation Video Guide

6 Obtain the code for the course

7 Course Folder Walkthrough

8 Your first deep learning model

**Data**

9 Section 2 Intro

10 Exercise 1 Solution

11 Exercise 2 Presentation

12 Exercise 2 Solution

13 Exercise 3 Presentation

14 Exercise 3 Solution

15 Exercise 4 Presentation

16 Exercise 4 Solution

17 Exercise 5 Presentation

18 Exercise 5 Solution

19 Tabular data

20 Data exploration with Pandas code along

21 Visual data Exploration

22 Plotting with Matplotlib

23 Unstructured Data

24 Images and Sound in Jupyter

25 Feature Engineering

26 Exercise 1 Presentation

**Machine Learning**

27 Section 3 Intro

28 Evaluating Performance code along

29 Classification

30 Classification code along

31 Overfitting

32 Cross Validation

33 Cross Validation code along

34 Confusion matrix

35 Confusion Matrix code along

36 Feature Preprocessing code along

37 Exercise 1 Presentation

38 Machine Learning Problems

39 Exercise 1 solution

40 Exercise 2 Presentation

41 Exercise 2 solution

42 Supervised Learning

43 Linear Regression

44 Cost Function

45 Cost Function code along

46 Finding the best model

47 Linear Regression code along

48 Evaluating Performance

**Deep Learning Intro**

49 Section 4 Intro

50 Exercise 1 Presentation

51 Exercise 1 Solution

52 Exercise 2 Presentation

53 Exercise 2 Solution

54 Exercise 3 Presentation

55 Exercise 3 Solution

56 Exercise 4 Presentation

57 Exercise 4 Solution

58 Deep Learning successes

59 Neural Networks

60 Deeper Networks

61 Neural Networks code along

62 Multiple Outputs

63 Multiclass classification code along

64 Activation Functions

65 Feed forward

**Gradient Descent**

66 Section 5 Intro

67 Learning Rate code along

68 Gradient Descent

69 Gradient Descent code along

70 EWMA

71 Optimizers

72 Optimizers code along

73 Initialization code along

74 Inner Layers Visualization code along

75 Exercise 1 Presentation

76 Exercise 1 Solution

77 Derivatives and Gradient

78 Exercise 2 Presentation

79 Exercise 2 Solution

80 Exercise 3 Presentation

81 Exercise 3 Solution

82 Exercise 4 Presentation

83 Exercise 4 Solution

84 Tensorboard

85 Backpropagation intuition

86 Chain Rule

87 Derivative Calculation

88 Fully Connected Backpropagation

89 Matrix Notation

90 Numpy Arrays code along

91 Learning Rate

**Convolutional Neural Networks**

92 Section 6 Intro

93 Convolution in 2 D

94 Image Filters code along

95 Convolutional Layers

96 Convolutional Layers code along

97 Pooling Layers

98 Pooling Layers code along

99 Convolutional Neural Networks

100 Convolutional Neural Networks code along

101 Weights in CNNs

102 Beyond Images

103 Features from Pixels

104 Exercise 1 Presentation

105 Exercise 1 Solution

106 Exercise 2 Presentation

107 Exercise 2 Solution

108 MNIST Classification

109 MNIST Classification code along

110 Beyond Pixels

111 Images as Tensors

112 Tensor Math code along

113 Convolution in 1 D

114 Convolution in 1 D code along

**Cloud GPUs**

115 Google Colaboratory GPU notebook setup

116 Floyd GPU notebook setup

**Recurrent Neural Networks**

117 Section 8 Intro

118 Exercise 1 Presentation

119 Exercise 1 Solution

120 Exercise 2 Presentation

121 Exercise 2 Solution

122 Time Series

123 Sequence problems

124 Vanilla RNN

125 LSTM and GRU

126 Time Series Forecasting code along

127 Time Series Forecasting with LSTM code along

128 Rolling Windows

129 Rolling Windows code along

**Improving performance**

130 Section 9 Intro

131 Image Generator code along

132 Hyperparameter search

133 Embeddings

134 Embeddings code along

135 Movies Reviews Sentiment Analysis code along

136 Exercise 1 Presentation

137 Exercise 1 Solution

138 Exercise 2 Presentation

139 Exercise 2 Solution

140 Exercise 3 Presentation

141 Learning curves

142 Learning curves code along

143 Batch Normalization

144 Batch Normalization code along

145 Dropout

146 Dropout and Regularization code along

147 Data Augmentation

148 Continuous Learning