Amazon Machine Learning LiveLessons

Amazon Machine Learning LiveLessons
Amazon Machine Learning LiveLessons
English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 3h 28m | 776 MB

Introduction

Module 1: Amazon Machine Learning Basics

Lesson 1: Introduction
Learning objectives
1.1 What is Machine Learning?
1.2 Machine Learning on AWS: Platform Services
1.3 Machine Learning on AWS: Application Services
1.4 Amazon ML Service
1.5 Who Should use Amazon ML?
1.6 Artificial Intelligence vs. Machine Learning
1.7 What are the Benefits of Machine Learning?

Lesson 2: Which Use Cases Can Amazon ML Solve?
Learning objectives
2.1 Personalization
2.2 Search
2.3 Marketing
2.4 Finance
2.5 Personal Productivity
2.6 Product Management

Lesson 3: How Does Amazon ML Work?
Learning objectives
3.1 High Level Overview
3.2 Options for Data Sources
3.3 Supervised Machine Learning
3.4 Unsupervised Machine Learning (Deep Learning)
3.5 Life Cycle of ML Processing
3.6 What are the Amazon ML Supervised Machine Learning Algorithms?

Lesson 4: Practical Applications for Machine Learning
Learning objectives
4.1 How to Frame a Suitable Problem
4.2 Scenario 1 – Identifying Bots
4.3 Scenario 2 – Predicting Pricing
4.4 Scenario 3 – Predicting Choice
4.5 Scenario 4 – Fraud Detection
4.6 Curator Project Sample Business Problem for this Course
4.7 Best Practices for Selecting a Business Problem

Lesson 5: Interactive Lab: Set up S3 Bucket for Amazon ML Usage
Learning objectives
5.1 Create and Configure S3 Bucket

Module 2: Amazon Machine Learning Data Architecture

Lesson 6: Information Architecture
Learning objectives
6.1 What are Features?
6.2 What is a Target?
6.3 What are Observations?
6.4 What is Labeled Data?
6.5 What is Unlabeled Data?
6.6 What is Ground Truth?
6.7 What is Input Data?
6.8 What is the Best Kind of Data?

Lesson 7: Interactive Lab: Prepare Data
Learning objectives
7.1 Where can you get Sample Data?
7.2 Collect Source Data for a Regression Model
7.3 Format Requirements for CSV File
7.4 Examining the CSV File
7.5 Collect Source Data for a Multi Class Model

Lesson 8: Data Preparation
Learning objectives
8.1 A Closer Look at the Input Data
8.2 Interactive Lab: Scrubbing the Data

Module 3: Data and Schema Configuration

Lesson 9: Interactive Lab: Upload Data File to S3
Learning objectives
9.1 Create Folder in S3 Bucket
9.2 Upload Data

Lesson 10: Interactive Lab: Amazon Machine Learning Dashboard
Learning objectives
10.1 Login to AWS Console
10.2 Machine Learning Service in Console
10.3 Regions that Support Amazon ML
10.4 Amazon ML Dashboard

Lesson 11: Interactive Lab: Set up the Datasource
Learning objectives
11.1 Create a New Datasource
11.2 Set Permissions and Verify Datasource

Lesson 12: Interactive Lab: Refine Schema
Learning objectives
12.1 Interpret Schema
12.2 Schema Data Types
12.3 Adjust Data Types
12.4 Identify the Target
12.5 Finalize Schema and Data Source
12.6 Handling Missing Values

Module 4: Machine Learning Visualization and Modeling

Lesson 13: Interactive Lab: Data Insights and Visualization Tools
Learning objectives
13.1 What are the Benefits of the Data Insights Tool?
13.2 What can we Examine with the Data Insights Tool?
13.3 Interactive Lab: Exploring Target Distributions
13.4 Interactive Lab: Identify Missing Value Distributions
13.5 Interactive Lab: Identify Invalid Data
13.6 Interactive Lab: Other Notable Observations

Lesson 14: Interactive Lab: Create a New Amazon ML Model
Learning objectives
14.1 Create Model from Data Insights Page
14.2 Configure Model Settings
14.3 Data Splitting

Lesson 15: Interactive Lab: Model Evaluation and Insights
Learning objectives
15.1 What Happens in an Evaluation?
15.2 Amazon ML Model Summary
15.3 Model Insights: Evaluation Summary
15.4 Model Insights: Evaluation Alerts
15.5 Evaluate Model Performance

Lesson 16: How to Refine a Model
Learning objectives
16.1 Refining Amazon ML Model Evaluations
16.2 Request a Brand New Evaluation
16.3 Massage the Data
16.4 Decrease / Increase Attributes
16.5 Create a Custom Recipe

Module 5: Predictions with Amazon Machine Learning

Lesson 17: Predictions
Learning objectives
17.1 How do Predictions Work?
17.2 What are the Types of Predictions?
17.3 Batch Predictions
17.4 Real-time Predictions

Lesson 18: Interactive Lab: Real-time Predictions
Learning objectives
18.1 Create Real-time Predictions
18.2 View Results

Lesson 19: Interactive Lab: Batch Predictions
Learning objectives
19.1 Create Prediction Data
19.2 Choose Model for Prediction
19.3 Create Prediction Datasource
19.4 Choose Destination for Predictions
19.5 Batch Prediction Summary
19.6 View the Manifest
19.7 Download Prediction Results from S3
19.8 View Prediction Results
19.9 Apply the Predictions

Lesson 20: Interactive Lab: Around the World with a Multiclass Model
Learning objectives
20.1 Using Machine Learning to Make Your Business More Powerful
20.2 Interactive Lab: Extract and Prepare Data
20.3 Interactive Lab: Create New Datasource and Multiclass Model
20.4 Interactive Lab: Examine Multiclass Model Summary
20.5 Understanding how Multiclass Models are Evaluated
20.6 Interactive Lab: Evaluate Multiclass Model Performance
20.7 Run Batch Predictions Against a Multiclass Model

Lesson 21: Final Review and Next Steps
Learning objectives
21.1 Review of Key Concepts
21.2 Questions to Consider
21.3 Call to Action

Summary

Table of Contents

1 Amazon Machine Learning – Introduction
2 Module introduction
3 Learning objectives
4 1.1 What is Machine Learning
5 1.2 Machine Learning on AWS – Platform Services
6 1.3 Machine Learning on AWS – Application Services
7 1.4 Amazon ML Service
8 1.5 Who Should use Amazon ML
9 1.6 Artificial Intelligence vs. Machine Learning
10 1.7 What are the Benefits of Machine Learning
11 Learning objectives
12 2.1 Personalization
13 2.2 Search
14 2.3 Marketing
15 2.4 Finance
16 2.5 Personal Productivity
17 2.6 Product Management
18 Learning objectives
19 3.1 High Level Overview
20 3.2 Options for Data Sources
21 3.3 Supervised Machine Learning
22 3.4 Unsupervised Machine Learning (Deep Learning)
23 3.5 Life Cycle of ML Processing
24 3.6 What are the Amazon ML Supervised Machine Learning Algorithms
25 Learning objectives
26 4.1 How to Frame a Suitable Problem
27 4.2 Scenario 1 – Identifying Bots
28 4.3 Scenario 2 – Predicting Pricing
29 4.4 Scenario 3 – Predicting Choice
30 4.5 Scenario 4 – Fraud Detection
31 4.6 Curator Project Sample Business Problem for this Course
32 4.7 Best Practices for Selecting a Business Problem
33 Learning objectives
34 5.1 Create and Configure S3 Bucket
35 Module introduction
36 Learning objectives
37 6.1 What are Features
38 6.2 What is a Target
39 6.3 What are Observations
40 6.4 What is Labeled Data
41 6.5 What is Unlabeled Data
42 6.6 What is Ground Truth
43 6.7 What is Input Data
44 6.8 What is the Best Kind of Data
45 Learning objectives
46 7.1 Where can you get Sample Data
47 7.2 Collect Source Data for a Regression Model
48 7.3 Format Requirements for CSV File
49 7.4 Examining the CSV File
50 7.5 Collect Source Data for a Multi Class Model
51 Learning objectives
52 8.1 A Closer Look at the Input Data
53 8.2 Interactive Lab – Scrubbing the Data
54 Module introduction
55 Learning objectives
56 9.1 Create Folder in S3 Bucket
57 9.2 Upload Data
58 Learning objectives
59 10.1 Login to AWS Console
60 10.2 Machine Learning Service in Console
61 10.3 Regions that Support Amazon ML
62 10.4 Amazon ML Dashboard
63 Learning objectives
64 11.1 Create a New Datasource
65 11.2 Set Permissions and Verify Datasource
66 Learning objectives
67 12.1 Interpret Schema
68 12.2 Schema Data Types
69 12.3 Adjust Data Types
70 12.4 Identify the Target
71 12.5 Finalize Schema and Data Source
72 12.6 Handling Missing Values
73 Module introduction
74 Learning objectives
75 13.1 What are the Benefits of the Data Insights Tool
76 13.2 What can we Examine with the Data Insights Tool
77 13.3 Interactive Lab – Exploring Target Distributions
78 13.4 Interactive Lab – Identify Missing Value Distributions
79 13.5 Interactive Lab – Identify Invalid Data
80 13.6 Interactive Lab – Other Notable Observations
81 Learning objectives
82 14.1 Create Model from Data Insights Page
83 14.2 Configure Model Settings
84 14.3 Data Splitting
85 Learning objectives
86 15.1 What Happens in an Evaluation
87 15.2 Amazon ML Model Summary
88 15.3 Model Insights – Evaluation Summary
89 15.4 Model Insights – Evaluation Alerts
90 15.5 Evaluate Model Performance
91 Learning objectives
92 16.1 Refining Amazon ML Model Evaluations
93 16.2 Request a Brand New Evaluation
94 16.3 Massage the Data
95 16.4 Decrease _ Increase Attributes
96 16.5 Create a Custom Recipe
97 Module introduction
98 Learning objectives
99 17.1 How do Predictions Work
100 17.2 What are the Types of Predictions
101 17.3 Batch Predictions
102 17.4 Real-time Predictions
103 Learning objectives
104 18.1 Create Real-time Predictions
105 18.2 View Results
106 Learning objectives
107 19.1 Create Prediction Data
108 19.2 Choose Model for Prediction
109 19.3 Create Prediction Datasource
110 19.4 Choose Destination for Predictions
111 19.5 Batch Prediction Summary
112 19.6 View the Manifest
113 19.7 Download Prediction Results from S3
114 19.8 View Prediction Results
115 19.9 Apply the Predictions
116 Learning objectives
117 20.1 Using Machine Learning to Make Your Business More Powerful
118 20.2 Interactive Lab – Extract and Prepare Data
119 20.3 Interactive Lab – Create New Datasource and Multiclass Model
120 20.4 Interactive Lab – Examine Multiclass Model Summary
121 20.5 Understanding how Multiclass Models are Evaluated
122 20.6 Interactive Lab – Evaluate Multiclass Model Performance
123 20.7 Run Batch Predictions Against a Multiclass Model
124 Learning objectives
125 21.1 Review of Key Concepts
126 21.2 Questions to Consider
127 21.3 Call to Action
128 Amazon Machine Learning – Summary


Download from Rapidgator

Download from Turbobit