Knowledge Graph Solutions using Neo4j

In this lesson, we will provide an overview of the section as well as cover what is a Graph or Network Graph

In this lesson, we will cover Movie Recommendation Problem.  We will use this problem all throughout this course to cover basics of Graph and Knowledge Graph as well as demonstrate various tools and library functions associated with Neo4j

In this lecture we will look broadly at the Knowledge Graph basic definitions and more specifically in the area of Network Graph & Related Tools.

In this lesson, we will provide brief overview on key features and capabilities of a Knowledge Graph.

It will help you classify a Graph solution that goes from Network graph to knowledge graph and kind of analytics expected when you move from network graph to a knowledge graph. This will aid in your understanding in Designing / prototyping a Graph engagement. The experience gained here can be used to design and build Graph Insights engagement with your customers, suppliers and employees.

In this lecture, we will conduct a quick demonstration of key Neo4j capabilities like Cypher, various plug-ins like Neosemantics, GDS and visualization tool like Bloom.

In this lesson, we will provide a summary i.e. a recap of the key takeaways from this Knowledge Graph Overview section

In this  lesson, we will provide an overview of the User scenario for our Movie Recommendation problem which will be used for demonstrating key features and capabilities of a Knowledge Graph driven solution using Neo4j tools.

In this lecture, we will show you how to set up your personal instance of Neo4j. Please note that many corporations have corporate agreements with Neo4j. While you can use this personal instance for learning purpose, please check with your IT technology team regarding using Neo4j for broader purposes. Also, if your organization has an approved instance and forbids you from creating a personal instance, please seek their process for procuring the license or cloud subscription.

In this lecture we will cover how to define Graph (nodes and relationships) for our Movie Graph project using Cypher query language. 

In this lecture we will cover few class exercise to demonstrate how to write Cypher queries to explore our Movie Rating Graph project

Let’s summarize key findings on this section Setup, specifically how to perform basic Graph capabilities in Neo4j after sandbox is set up

In this lesson, we will cover basic aspect of Graph data base setup including how to set up graph nodes and relationship from various data sources. We will also identify various queries to demonstrate how to explore graph and execute queries of interest to your Movie Graph project.

This lesson will focus primarily on identifying various data sources for setting up Movie graph and the initial graph data model for setting up in Neo4j.

In this lecture, we will cover how to start your first Graph project in Neo4j

In this lecture we will provide steps needed to load your data into Neo4j Graph using datasources defined in lecture 2.  We will create basic nodes associated with Movie, TMDB, IMDB and Artist

This lecture will cover steps needed to create relationships between various nodes created in last lecture

In this lecture, we will cover how to execute first set of class queries associated with “Explore Graph” in Neo4j using Cypher language

In this lecture, we will cover how to execute second class of queries as defined in the very first lecture 1

In this lesson we are summarizing section contents and are using some exercises to demonstrate how to conduct "Search", "Match" and "Recommend" on our Movie Rating Graph using Cypher query language

In this lesson, we will introduce features and capabilities of Knowledge Graph.  We will also provide overview of various Neo4j libraries needed to support Knowledge Graph features and capabilities

In this lecture, we will introduce one of the  Neo4j libraries such as APOC.  We will provide details on Neo4j’s plug-in APOC with several examples

In this lecture, we will cover another important Advanced Knowledge Graph technology concept for ingesting external ontologies.

Neo4j’s n10s - Neosemantics gives us the opportunity to ingest public and private ontologies. We will cover what is ontology and how we upload and use ontologies using Neosemantics.

We have seen unprecedented growth in the use of machine learning and deep learning techniques along with Graphs, making Graph the center point for knowledge generation, consolidation and visualization. In this section, we will introduce machine learning using an example that drove most of the initial successes. Please note, this is an introductory course. For those of you who are interested in this area, we will be introducing intermediate and advanced course work and can also connect you to other advanced material in this area.

Neo4j Graph Data Science Library offers variety of machine learning techniques using graphs. In this lesson, we will provide overview of some of these GDS algorithms and will provide examples for our Movie project

In this lesson, we will cover graph visualization tool called Bloom designed specifically to allow end users or business analysts to explore any sub-graph or search any complex graph traversal using natural language syntax.

In this lesson, we will discuss how to integrate Neo4j graph seamlessly with Python for either creating graph nodes and relationships within Python environment or running any data science/machine learning libraries for additional analytics work

In this lecture, we will summarize section contents

In this lecture, we will summarize course contents and will cover how various Neo4j's libraries and tools can be used to migrate from a Network Graph t0 a Knowledge Graph

In this lecture we well provide References and Recommended Readings as it relates to our course on "Knowledge Graph Solutions using Neo4j"

Thanks to you for successfully completing this course.  We look forward to seeing you in our other AI and Knowledge Graph related courses.

This lesson list additional course offering with Applied AI institute in various AI related topics