TensorFlow and the Google Cloud ML Engine for Deep Learning

TensorFlow and the Google Cloud ML Engine for Deep Learning

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 17h 28m | 3.82 GB

CNNs, RNNs and other neural networks for unsupervised and supervised deep learning

TensorFlow is quickly becoming the technology of choice for deep learning, because of how easy TF makes it to build powerful and sophisticated neural networks. The Google Cloud Platform is a great place to run TF models at scale, and perform distributed training and prediction. This is a comprehensive, from-the-basics course on TensorFlow and building neural networks. It assumes no prior knowledge of Tensorflow, all you need to know is basic Python programming.

This course focus is to on learning by doing examples. All code files provided to refer and learn.

What You Will Learn

  • Build and execute machine learning models on TensorFlow
  • Implement Deep Neural Networks, Convolutional Neural Networks, and Recurrent Neural Networks
  • Understand and implement unsupervised learning models such as Clustering and Autoencoders
Table of Contents

1 You, This Course and Us
2 Install TensorFlow
3 Install Jupyter Notebook
4 Lab – Setting up A GCP Account
5 Lab – Using the Cloud Shell
6 Datalab ~ Jupyter
7 Lab – Creating and Working On a Datalab Instance
8 Introducing Machine Learning
9 Representation Learning
10 Neural Networks Introduced
11 Introducing TensorFlow
12 Lab – Simple Math Operations
13 Computation Graph
14 Tensors
15 Lab – Tensors
16 Linear Regression Intro
17 Placeholders and Variables
18 Lab – Placeholders
19 Lab – Variables
20 Lab – Linear Regression with Made-up Data
21 Image Processing
22 Images As Tensors
23 Reading and Working with Images
24 Lab – Image Transformations
25 Introducing MNIST
26 K-Nearest Neighbours as Unsupervised Learning
27 One-hot Notation and L1 Distance
28 Steps in the K-Nearest-Neighbours Implementation
29 Lab – K-Nearest-Neighbours
30 Learning Algorithm
31 Individual Neuron
32 Learning Regression
33 Learning XOR
34 XOR Trained
35 Lab – Access Data from Yahoo Finance
36 Non TensorFlow Regression
37 Lab – Linear Regression – Setting Up a Baseline
38 Gradient Descent
39 Lab – Linear Regression
40 Lab – Multiple Regression in TensorFlow
41 Logistic Regression Introduced
42 Linear Classification
43 Lab – Logistic Regression – Setting Up a Baseline
44 Logit
45 Softmax
46 Argmax
47 Lab – Logistic Regression
48 Estimators
49 Lab – Linear Regression using Estimators
50 Lab – Logistic Regression using Estimators
51 Traditional Machine Learning
52 Deep Learning
53 Operation of a Single Neuron
54 The Activation Function
55 Training a Neural Network – Back Propagation
56 Lab – Automobile Price Prediction – Exploring the Dataset
57 Lab – Automobile Price Prediction – Using TensorFlow for Prediction
58 Hyperparameters
59 Vanishing and Exploding Gradients
60 The Bias-Variance Trade-off
61 Preventing Overfitting
62 Lab – Iris Flower Classification
63 Classification as an ML Problem
64 Confusion Matrix – Accuracy, Precision and Recall
65 Decision Thresholds and the Precision-Recall Trade-off
66 F1 Scores and the ROC Curve
67 Mimicking the Visual Cortex
68 Convolution
69 Choice of Kernel Functions
70 Zero Padding and Stride Size
71 CNNs vs DNNs
72 Feature Maps
73 Pooling
74 Lab – Classification of Street View House Numbers – Exploring the Dataset
75 Basic Architecture of a CNN
76 Lab – Classification of Street View House Numbers – Building the Model
77 Lab – Classification of Street View House Numbers – Running the Model
78 Lab – Building a CNN Using the Estimator API
79 Learning from the Past
80 Unrolling an RNN Cell through Time
81 Training an RNN – Back Propagation through Time
82 Lab – RNNs for Image Classification
83 Vanishing and Exploding Gradients in an RNN
84 Long Memory Neurons vs Truncated BPTT
85 The Long_Short Term Memory Cell
86 A Sequence of Words
87 Text in Numeric Form
88 Lab – Sentiment Analysis on Rotten Tomatoes Reviews – Exploring the Dataset
89 Lab – Sentiment Analysis on Rotten Tomatoes Reviews – Building, Running the Model
90 Supervised and Unsupervised Learning
91 Expressing Attributes as Numbers
92 K-Means Clustering
93 Lab – K-Means Clustering with 2-Dimensional Points in Space
94 Lab – K-Means Clustering with Images
95 Patterns in Data
96 Principal Components Analysis
97 Autoencoders
98 Autoencoder Neural Network Architecture
99 Lab – PCA on Stock Data – Matplotlib vs Autoencoders
100 Stacked Autoencoders
101 Lab – Stacked Autoencoder with Dropout
102 Lab – Stacked Autoencoder with Regularization and He Initialization
103 Denoising Autoencoders
104 Lab – Denoising Autoencoder with Gaussian Noise
105 Lab – Taxicab Prediction – Setting up the dataset
106 Lab – Taxicab Prediction – Training and Running the model
107 A Taxicab Fare Prediction Problem
108 Datalab
109 Querying BigQuery
110 Explore Data
111 Clean Data
112 Benchmark
113 Using TensorFlow
114 The Estimator API
115 The Experiment Function
116 Introduction to Cloud MLE
117 Using Cloud MLE
118 The Training Service
119 The Prediction Service
120 Feature Engineering to the rescue
121 New Approach
122 Dataflow Create Pipeline
123 Dataflow Run Pipeline
124 Feature Engineering
125 Deep and Wide Models
126 Hyperparameter Tuning
127 Hyperparameter Tuning on the GCP