In this talk, we'll discuss computer vision and the kinds of graph modeling techniques that lend themselves well to this domain. We will utilize a few sample use cases and explore the utilization of a graph-based model and some of its potential alternatives, including some considerations and trade-offs.
We'll share insights into why graphs may be useful for this purpose and explore what makes a neural network a graph neural network. We'll also discuss some of the inherent challenges, such as defining convolutions on graphs.
We'll explore this model representation as well as some of the architectural and implementation considerations. These use cases will be based on real-world examples but may use generated data if/where necessary.
Speakers: Anuj Agrawal
Format: Lighting Talk 10-15 min
Level: Intermediate
Topics: #GraphDataScience, #MachineLearning, #General, #AerospaceandDefense, #Biotechnology, #Intermediate
Region: AMERICAS
Visit https://development.neo4j.dev/nodes-2022 learn more at https://development.neo4j.dev/developer/get-started and engage at https://community.neo4j.com