Deep Learning Meet-up #17

##### Share, Exchange and Learn ######

Please join our Facebook group for knowledge exchange & updates:
https://www.facebook.com/groups/deeplearninghk

& our github page for materials in previous tech updates section:
https://github.com/deep-learning-hk/agenda

=======================================================================

Let's have some good exchanges with all other DL practitioners, and also challenge our understanding about DL concepts.

** We encourage everyone to at least bring one topic to share (can be as short as 1 min), it doesn't matter it's a big research finding, a new ML tool, a small trick in making more stable loss function or anything interesting happening in DL/ML world, let's build our DL community in HK. ; )

=======================================================================

Open topics:

1. Efficient Large-Scale Fleet Management via Multi-Agent Deep
   Reinforcement Learning [KDD2018, accepted paper]

Experts from Lalamove would share how to employ algorithm to build an efficient fleet management system.

reference:
https://www.kdd.org/kdd2018/accepted-papers/view/efficient-large-scale-fleet-management-via-multi-agent-deep-reinforcement-l

2. Production of ML model, in GCP's Kubernetes
   After showing how to put all things into Docker and deploy the ML model into a GCP Compute Engine as the most simple way, we will move one step further to deploy a ML model in Kubernetes Engine in GCP, so we can enjoy its scalability, fault-tolerance and all other benefits.

3. Kaggle Competition Sharing
   Yes, it's your time to share your fun experience in Kaggle competition. Walk us through the notebook!

Agenda:
1:00 - 1:30pm - Intro and Tech updates from everyone
1:30pm - 3:00pm - Open Topic 1
3:00pm - 3:45pm - break
3:45pm - around 5:30pm - Open Topic 2 & 3

== Special thanks for Lalamove's sponsorship for the venue ==