Serverless Meetup at PubNub


Details
• What we'll do
Agenda
• 6:00 pm - Gathering and Networking
• 6:20 pm - Opening
• 6:30 pm - An Introduction to Serverless Components by Brian Neisler, Head of Product at Serverless Inc.
• 7:00 pm - Build an IoT Backend with Serverless, Node.js and Docker, by Al Tsang, CEO & Founder at LunchBadger
• 7:30 pm - How to deploy DL models on AWS Lambda, by Rustem Feyzkhanov, Data Scientist at Astro Digital
• 8:00 pm - Closing
Abstracts
An Introduction to Serverless Components, by Brian Neisler, Head of Product at Serverless Inc.
A quick look into a new feature of the Serverless Framework which offers users a universal way to provision resources, features and applications across all Cloud and SaaS infrastructure.
Build an IoT Backend with Serverless, Node.js and Docker, by Al Tsang, CEO & Founder at LunchBadger
Join Al Tsang, the CEO of LunchBadger to learn how to build, scale and operate an IoT backend with microservices running Serverless. This session will provide a getting started guide in addition to examples of how to develop and run IoT backends as FaaS (Functions as a Service) using an API Gateway, Kubernetes, Node.js and Docker.Reference architectures and open source code samples will be provided.
How to deploy DL models on AWS Lambda, by Rustem Feyzkhanov, Data Scientist at Astro Digital
This year tensorflow 1.4 was finally released. I succeeded to fit it into AWS Lambda and built recognition of images trained on imagenet. Why? Given the price tag lambda one run (recognition of one picture) will cost $0.00005. That is, for a dollar you can recognize 20,000 images. It is much cheaper than almost any alternatives, though completely scalable (1000 functions can be run in parallel), and can be easily integrated into cloud infrastructure. If you have a trained model in your pocket my talk will help you to fit it into AWS Lambda.
During the meetup I will also show how to start tensorflow package using serverless framework in one line of code.
• What to bring
Lots of enthusiasm...
• Important to know
Please enter the building on the side which is on Ringold St. The front entrance will be closed.

Serverless Meetup at PubNub