How Netflix deploys pre-trained Deep Learning models in AWS using DJL

ZOOM LINK:
https://tinyurl.com/aws-djl

ABSTRACT:
In this talk, we will introduce Deep Java Library (DJL), an open source deep learning toolkit for Java developers to build and deploy deep learning models in Java ecosystem. We will show you how to use DJL to deploy pre-trained open source NLP/object detection models out of box from your Java/Scala-based big data pipeline (i.e., Spark, Kafka, Flink, Scio, Akka-stream, etc…) for processing, standardizing and analyzing unstructured data.

SPEAKER(S) BIOS:

1. Gautam Kumar, Senior Software Engineer, Amazon
   LinkedIn: https://www.linkedin.com/in/gautam-kumar-03140815/
   Twitter: @gautam5669

Gautam has developed AWS Deep Learning Containers, AWS Deep Learning AMI and SageMaker operators for Kubernetes. He is passionate about building tools and systems for AI. In his spare time, he enjoy biking and reading books.

2. Stanislav Kirdey, Senior Software Engineer, Netflix
   LinkedIn: https://www.linkedin.com/in/skirdey/
   Blog: https://stankirdey.com/

Stanislav works at Netflix where he focuses on large scale applied machine learning in the areas of NLP, search, and anomaly detection. Outside of Machine Learning and work, Stanislav is obsessed with RuPaul's Drag Race, POSE and Star Trek.

DURATION:

• Tech talk presentation: 45min
• Demo and Q&A: 15min

ZOOM LINK:
https://tinyurl.com/aws-djl