Put AI to Work
April 15-18, 2019
New York, NY

Put deep learning to work: A practical introduction using Amazon Web Services (Day 2)

Wenming Ye (Amazon Web Services)
Location: Sutton Center

Who is this presentation for?

An aspiring ML Developer, practicing ML Developer and/or Data Scientist.

Prerequisite knowledge


What you'll learn

* Deep Learning, TensorFlow, PyTroch, and MXNet * Key trends and business scenarios in AI/DL adoption * Bring your models to production faster, with much less effort, and lower cost.


Machine learning (ML) and deep learning (DL) projects are becoming increasingly common at enterprises and startups alike and have been a key innovation engine for Amazon businesses such as Go, Alexa, and Robotics.

In this 2 day training, Wenming Ye (AWS) and Miro Enev (Nvidia) offer a practical next step in DL learning with instructions, demos, and hands-on labs. You will explore the current trends powering AI/DL adoption and algorithmic learning in neural networks, dive into how DL is applied in modern business practices, and leverage building blocks from the Amazon ML family of AI services from powerful new GPU instances, convenient Amazon SageMaker built-in Algorithms, to ready-to-use managed AI services.

Day 1

  • Deep learning and reinforcement learning trends
  • Neural learning and common DL architectures
  • Understanding a DL project workflow by example
  • Introduction to high level Amazon ML Services
  • Amazon SageMaker (a Jupyter-based service) with Amazon Elastic Inference
  • Running Tensorflow and PyTorch on SageMaker

Day 2

  • Group discussion: bring your own deep learning problem
  • SageMaker custom and built-in Algorithms
  • Time series prediction using recurrent neural networks
  • Current Topics in NLP
  • Introduction to reinforcement learning and the AWS DeepRacer
Photo of Wenming Ye

Wenming Ye

Amazon Web Services

Wenming Ye is an AI and ML solutions architect at Amazon Web Services, helping researchers and enterprise customers use cloud-based machine learning services to rapidly scale their innovations. Previously, Wenming had diverse R&D experience at Microsoft Research, an SQL engineering team, and successful startups.