Oreilly – Graph-Powered Machine Learning, Video Edition 2022-6

Oreilly – Graph-Powered Machine Learning, Video Edition 2022-6 Downloadly IRSpace

Apr 18, 2025 - 18:31 Updated: Aug 17, 2025 - 18:27

0 0

Oreilly – Graph-Powered Machine Learning, Video Edition 2022-6

Graph-Powered Machine Learning Video Edition. This course is a unique and complete experience for machine learning enthusiasts. In this course, you will enhance your machine learning models using graph-based algorithms, which are an ideal structure for complex and related data.

What you will learn:

The full cycle of a machine learning project: You will learn a complete machine learning project from start to finish.
Graphs in Big Data Platforms: You will explore the role of graphs in processing huge amounts of data.
Modeling Data Sources Using Graphs: You will learn how to model your data as graphs.
Natural language processing, recommender systems, and graph-based fraud detection: You will learn advanced techniques for solving various challenges in the fields of machine learning.
Graph Algorithms: You will gain an in-depth understanding of various graph algorithms and learn how to use them.
Working with Neo4J: You will learn how to use one of the most widely used graph databases in a practical way.

This course is suitable for people who:

Are familiar with the basic concepts of machine learning.
They are looking to improve their skills in the field of machine learning.
Seeking a deep understanding of graph-based algorithms.
Interested in practical applications of graph-based machine learning in the real world.

Graph-Powered Machine Learning Video Edition Course Specifications

Publisher: Oreilly
Instructor: Alessandro Negro
Training level: Beginner to advanced
Training duration: 12 hours and 34 minutes
Number of lessons: 84

Course headings

Part 1 Introduction
Chapter 1 Machine learning and graphs: An introduction
Chapter 1 Business understanding
Chapter 1 Machine learning challenges
Chapter 1 Performance
Chapter 1 Graphs
Chapter 1 Graphs as models of networks
Chapter 1 The role of graphs in machine learning
Chapter 2 Graph data engineering
Chapter 2 Velocity
Chapter 2 Graphs in the big data platform
Chapter 2 Graphs are valuable for big data
Chapter 2 Graphs are valuable for master data management
Chapter 2 Graph databases
Chapter 2 Sharding
Chapter 2 Native vs. non-native graph databases
Chapter 2 Label property graphs
Chapter 3 Graphs in machine learning applications
Chapter 3 Managing data sources
Chapter 3 Detect a fraud
Chapter 3 Recommended items
Chapter 3 Algorithms
Chapter 3 Find keywords in a document
Chapter 3 Storing and accessing machine learning models
Chapter 3 Monitoring a subject
Chapter 3 Visualization
Chapter 3 Leftover: Deep learning and graph neural networks
Part 2 Recommendations
Chapter 4 Content-based recommendations
Chapter 4 Representing item features
Chapter 4 Representing item features
Chapter 4 User modeling
Chapter 4 Providing recommendations
Chapter 4 Providing recommendations
Chapter 4 Providing recommendations
Chapter 5 Collaborative filtering
Chapter 5 Collaborative filtering recommendations
Chapter 5 Computing the nearest neighbor network
Chapter 5 Computing the nearest neighbor network
Chapter 5 Providing recommendations
Chapter 5 Dealing with the cold-start problem
Chapter 6 Session-based recommendations
Chapter 6 The events chain and the session graph
Chapter 6 Providing recommendations
Chapter 6 Session-based k-NN
Chapter 7 Context-aware and hybrid recommendations
Chapter 7 Representing contextual information
Chapter 7 Providing recommendations
Chapter 7 Providing recommendations
Chapter 7 Advantages of the graph approach
Chapter 7 Providing recommendations
Part 3 Fighting fraud
Chapter 8 Basic approaches to graph-powered fraud detection
Chapter 8 Fraud prevention and detection
Chapter 8 The role of graphs in fighting fraud
Chapter 8 Warm-up: Basic approaches
Chapter 8 Identifying a fraud ring
Chapter 9 Proximity-based algorithms
Chapter 9 Distance-based approach
Chapter 9 Creating the k-nearest neighbors graph
Chapter 9 Identifying fraudulent transactions
Chapter 9 Identifying fraudulent transactions
Chapter 10 Social network analysis against fraud
Chapter 10 Social network analysis concepts
Chapter 10 Score-based methods
Chapter 10 Neighborhood metrics
Chapter 10 Centrality metrics
Chapter 10 Collective inference algorithms
Chapter 10 Cluster-based methods
Part 4 Taming text with graphs
Chapter 11 Graph-based natural language processing
Chapter 11 A basic approach: Store and access sequence of words
Chapter 11 NLP and graphs
Chapter 11 NLP and graphs
Chapter 12 Knowledge graphs
Chapter 12 Knowledge graph building: Entities
Chapter 12 Knowledge graph building: Relationships
Chapter 12 Semantic networks
Chapter 12 Unsupervised keyword extraction
Chapter 12 Unsupervised keyword extraction
Chapter 12 Keyword co-occurrence graph
Appendix A. Machine learning algorithms taxonomy
Appendix C Graphs for processing patterns and workflows
Appendix C Graphs for defining complex processing workflows
Appendix D. Representing graphs

Course images

Graph-Powered Machine Learning Video Edition

Sample course video

Installation Guide

After Extract, view with your favorite player.

Subtitles: None

Quality: 720p

Download link

Download Part 1 – 1 GB

Download Part 2 – 679 MB

File(s) password: www.downloadly.ir

File size

1.6 GB

Oreilly – Graph-Powered Machine Learning, Video Edition 2022-6