English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 12h 58m | 1.61 GB
Learn about cloud-based machine learning algorithms and how to integrate them with your applications
This course is designed to make you an expert in AWS machine learning and it teaches you how to convert your cool ideas into highly scalable products in a matter of days.The biggest challenge for a data science professional is how to convert the proof-of-concept models into actual products that your customers can use. There are several courses on machine learning that teach you how to build models in R, Python, Matlab and so forth. However, converting a model into a scalable solution and integrating with your existing application requires a lot of effort and development. The real success of your ideas and concepts depends on how soon you can put the capabilities in the hands of your customers.With the AWS Machine Learning service, you can easily conduct experiments and test your concepts. Once you are happy, you can instantly scale them to support millions of requests. No separate development work is needed.
This course is completely hands-on with examples using: AWS Web Console, Python Notebook Files, and Web clients built on AngularJS. You will also learn and integrate security into exercises using a variety of AWS provided capabilities including Cognito.
What You Will Learn
- Learn the AWS Machine Learning algorithms, Predictive quality assessment, Model optimization
- Integrate predictive models with your application using simple and secure APIs
- Convert your ideas into highly scalable products in days
Table of Contents
1 Introduction
2 Root Account Setup and Billing Dashboard Overview
3 Enable Access to Billing Data for IAM Users
4 Create Users Required For the Course
5 AWS Command Line Interface Tool Setup and Summary
6 Six Advantages of Cloud Computing
7 AWS Global Infrastructure Overview
8 SageMaker Overview
9 Compute Instance Families and Pricing
10 Algorithms and Data Formats Supported For Training and Inference
11 XGBoost – Introduction and Comparison with Other Approaches
12 Demo 1 – S3 Bucket Setup
13 Demo 2 – Setup Notebook Instance on SageMaker
14 Demo 3 – Source Code and Data Setup
15 Demo 4 – Create Files in SageMaker Data Formats and Save Files to S3
16 Demo 5 – Working with XGBoost – Linear Regression Straight Line Fit
17 Demo 6 – XGBoost Example with Quadratic Fit
18 Demo 7 – Kaggle Bike Rental Data Setup, Exploration and Preparation
19 Demo 8 – Kaggle Bike Rental Model Version 1
20 Demo 9 – Kaggle Bike Rental Model Version 2
21 Demo 10 – Kaggle Bike Rental Model Version 3
22 Demo 11 – Training on SageMaker Cloud – Kaggle Bike Rental Model Version 3
23 Demo 12 – Invoking SageMaker Model Endpoints for Real Time Predictions
24 Demo 13 – Invoking SageMaker Model Endpoints from Client Outside of AWS
25 XGBoost Hyper Parameter Tuning
26 Demo 14 – XGBoost Multi-Class Classification Iris Data
27 Demo 15 – XGBoost Binary Classifier for Diabetes Prediction
28 Demo 16 – XGBoost Binary Classifier for Edible Mushroom Prediction
29 Summary – XGBoost
30 Introduction PCA and SageMaker PCA
31 PCA Demo Source Code setup
32 Demo 1 – PCA with Random Dataset
33 Demo 2 – PCA with Correlated Dataset
34 Demo 3.1 – PCA with Kaggle Bike Sharing – Overview and Normalization
35 Demo 3.2 – PCA Local Model with Kaggle Bike Train
36 Demo 3.3 – PCA training with SageMaker
37 Demo 3.4 – PCA Projection with SageMaker
38 Summary
39 Introduction to Factorization Machines
40 Demo – Movie Recommender Data Preparation
41 Demo – Movie Recommender Model Training
42 Demo – Movie Predictions by User
43 Python Development Environment and Boto3 Setup
44 Project Source Code and Data Setup
45 Lab – Intro to Python Jupyter Notebook Environment, Pandas, Matplotlib
46 Lab – AWS S3 Bucket Setup and Configure Security
47 Summary
48 Machine Learning Terminology
49 Data Types supported by AWS Machine Learning
50 Linear Regression Introduction
51 Binary Classification Introduction
52 Multiclass Classification Introduction
53 Data Visualization – Linear, Log, Quadratic and More
54 Lab – Linear Model, Squared Error Loss Function, Stochastic Gradient Descent
55 Lab – Linear Regression for complex shapes
56 Summary
57 Lab – Simple Training Data
58 Lab – Datasource
59 Lab – Train Model with default recipe
60 Concept – How to evaluate regression model accuracy
61 Lab – Evaluate predictive quality of the trained model
62 Lab – Review Default Recipe Settings Used to Train model
63 Lab – Train Model with Custom Recipe and Review Performance
64 Model Performance Summary and Conclusion
65 Lab – Quadratic Fit Training Data
66 Lab – Under fitting with Linear Features
67 Lab – Normal Fit with Quadratic Features
68 Summary
69 Lab – Impact of Features with Different Magnitude
70 Concept – Normalization to smoothen magnitude differences
71 Lab – Train Model with Feature Normalization
72 Summary
73 Lab – Prepare Training Data
74 Lab – Adding Complex Features
75 Lab – Train Model with Higher Order Features
76 Lab – Performance of Model with Degree 1 Features
77 Lab – Performance of Model with Degree 4 Features
78 Lab – Performance of Model with Degree 15 Features
79 Summary
80 Review Kaggle Bike Train Problem and Dataset
81 Lab – Train Model to Predict Hourly Rental
82 Lab – Evaluate Prediction Quality
83 Linear Regression Wrap up and Summary
84 Binary Classification – Logistic Regression, Loss Function, Optimization
85 Lab – Binary Classification Approach
86 True Positive, True Negative, False Positive and False Negative
87 Lab – Logistic Optimization Objectives
88 Lab – Logistic Cost Function
89 Lab – Cost Example
90 Optimizing Weights
91 Summary
92 Problem Objective, Input Data and Strategy
93 Lab – Prepare For Training
94 Lab – Training a Classification Model
95 Concept – Classification Metrics
96 Concept – Classification Insights with AWS Histograms
97 Concept – AUC Metric
98 Lab – Review Diabetes Model Performance
99 Lab – Cutoff Threshold Interactive Testing
100 Lab – Evaluating Prediction Quality with Additional Dataset
101 Lab – Batch Prediction and Compute Metrics
102 Summary
103 Lab – Iris Classification
104 Lab – Train Classifier with Default and Custom Recipe
105 Concept – Evaluating Predictive Quality of Multiclass Classifiers
106 Concept – Confusion Matrix to Evaluating Predictive Quality
107 Lab – Evaluate Performance of Iris Classifiers using Default Recipe
108 Lab – Evaluate Performance of Iris Classifiers using Custom Recipe
109 Lab – Batch Prediction and Computing Metrics using Python Code
110 Summary
111 AWS Twitter Feed Classification for Customer Service
112 Lab – Train, Evaluate Model and Assess Predictive Quality
113 Lab – Interactive Prediction with AWS
114 Logistic Regression Summary
115 Recipe Overview
116 Recipe Example
117 Text Transformation
118 Numeric Transformation – Quantile Binning
119 Numeric Transformation – Normalization
120 Cartesian product Transformation – Categorical and Text
121 Summary
122 Introduction
123 Data Rearrangement, Maximum Model Size, Passes, Shuffle Type
124 Regularization, Learning Rate
125 Regularization Effect
126 Improving Model Quality
127 Model Maintenance
128 AWS Machine Learning System Limits
129 AWS Machine Learning Pricing
130 Introduction
131 Integration Scenarios
132 Security using IAM
133 Hands-on lab – List of Demos and Objective
134 Lab – Enable Real Time End Point and Configure IAM Prediction User
135 Lab – Invoking Prediction from AWS Command Line Interface
136 Lab – Invoking Prediction from Python Client
137 Lab – Python Client to Train, Evaluate Models and Integrate with AWS
138 Lab – Invoking Prediction from Web Page AngularJS Client
139 Demo Allowing Prediction Only For Registered Users
140 Cognito Overview
141 Lab – Cognito User Pool Configuration
142 Lab – AngularJS Web Client – Invoke Prediction for authorized users
143 Lab – Invoke Machine Learning Service From AWS EC2 Instance
144 Summary
145 Conclusion
Resolve the captcha to access the links!