Artificial Intelligence at the Edge - Jameson Toole - ODSC Meetup

Artificial Intelligence at the Edge - Jameson Toole - ODSC Meetup

AI is moving from the cloud to the edge | Presented By Dr. Jameson Toole
Dr. Jameson Toole
Dr. Jameson Toole
Co-founder and CEO,

Dr. Jameson Toole is the CEO and co-founder of Fritz - a platform for building tools to help developers optimize, deploy, and manage machine learning models on mobile devices. He holds undergraduate degrees in Physics, Economics, and Applied Mathematics from the University of Michigan as well as an M.S. and PhD in Engineering Systems from MIT. His work in the Human Mobility and Networks Lab at MIT centered on applications of big data and machine learning to urban and transportation planning. Prior to founding Fritz, Dr. Toole spent time building analytics pipelines for Google[X]’s Project Wing and running the data science team at Jana Mobile, a Boston technology startup.

Presentation Description

Artificial Intelligence at the Edge

Machine learning and AI models now outperform humans on tasks ranging from image recognition to language translation. However, sending video, audio, and other sensor data up to the cloud and back is too slow for apps like Snapchat, features like “Hey, Siri!”, and autonomous machines like self-driving cars. Developers seeking to provide seamless user experiences must now move their models down to devices on the edge of the network where they can run faster, at lower cost, and with greater privacy.

This talk outlines why developers should be deploying deep learning models to the edge, common roadblocks they will face, and how to overcome them. I begin by describing two major technological trends pushing machine learning out to the edge of the network: the rise of deep learning and the ubiquity of mobile sensors. I then discuss how developers can use these tools like Core ML and TensorFlow Lite to solve problems at 60 frames-per-second and create smooth, real-time experiences for users, all while securing data and reducing cloud costs.

Despite these benefits, transitioning to the edge can be difficult. Tech stacks used by machine learning specialists and mobile developers are mismatched, and it’s rare to find engineers fluent in both. Processing power, storage, and memory are all constrained, and developers need to ensure their models can run on hundreds of different devices. This talk offers advice to developers on how to deal with these challenges so their migration to the edge is as simple and painless as possible.

Presentation Curriculum

Artificial Intelligence at the Edge Webinar
Hide Content