Deep Learning for Engineers: Using Java to deploy Deep Learning models

This is a past event

187 people went

Details

Agenda:
6:00-7:00: Socializing (Thanks GridGain for food and drinks!)
7:00-7:10: Announcements
7:10-8:10: Deep Learning for Engineers: Using Java to deploy Deep Learning models
8:10-8:30: Q&A

Abstract:
AI is evolving rapidly, and much of the recent advancement is driven by Deep Learning, a machine learning technique inspired by the inner-working of the human brain. In this session, we will discuss what deep learning is, and the new capabilities it enables. We will dive into a few computer vision models that are demonstrating super-human performance, and to integrate these models into your existing Java system leveraging Apache MXNet - an open source deep learning framework – and MXNet’s Java API. By the end of the session, you will learn how to leverage deep learning models in your Java-based systems, the various gotchas involved, and where/how you learn more.

Speakers:

Andrew Ayres
Andrew is a SDE in Amazon Deep Engine and one of the authors of MXNet Java API. Previous work includes cryptography for the Key Management Service on AWS, machine learning for IBM Watson, and performing research at Oak Ridge National Laboratory. He graduated with a Ph.D. in Nuclear Physics from the University of Tennessee in 2014. While there his focus was on stellar nuclear reactions and supernova simulations.

Qing Lan
Qing is a SDE in Amazon Deep Engine and one of the authors of MXNet Java API. He graduated with a M.S. in Computer Engineering from Columbia University in 2017. He is experienced in Deep Learning, Programming Language Translator and distributed systems. Qing is also a Committer of Apache MXNet.