Put deep learning to work: A practical introduction using Amazon Web Services

Wenming Ye (Amazon Web Services), Miro Enev (NVIDIA), Mahendra Bairag (Amazon Web Services)

Monday, Sep 9 & Tuesday, Sep 10,
9:00am - 5:00pm

Location: 114

Secondary topics: Deep Learning tools, Machine Learning, Reinforcement Learning

Participants should plan to attend both days of this 2-day training course. To attend training courses, you must register for a Platinum or Training pass; does not include access to tutorials on Tuesday.

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. Wenming Ye, Miro Enev, and Mahendra Bairag detail a practical next step in DL learning with instructions, demos, and hands-on labs.

What you'll learn, and how you can apply it

Understand deep learning, TensorFlow, PyTorch, MXNet, and key trends and business scenarios in AI/DL adoption
Learn to bring your models to production faster, with much less effort, and at lower cost

Who is this presentation for?

You're an aspiring ML developer, practicing ML developer, or data scientist.

Prerequisites:

A working knowledge of Python

You’ll 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 using the Amazon ML family of AI services from powerful new GPU instances to convenient Amazon SageMaker built-in algorithms to ready-to-use managed AI services.

Outline

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

About your instructors

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.

Miro Enev is a senior solutions architect at NVIDIA, specializing in advancing data science and machine intelligence while respecting human values. He supports the Pacific Northwest teams engaged with cloud, industrial, and retail clients while participating in research in deep reinforcement learning and edge-to-cloud AI. Miro holds a PhD from the University of Washington’s computer science and engineering department, where his thesis was on machine learning applications for information privacy in emerging sensor contexts. He studied cognitive science and computer science as an undergraduate at the University of California, Berkeley.

Mahendra Bairagi is an Artificial Intelligence (AI) and Machine Learning (ML) specialist architect for Amazon Web Services, working on all things AI, ML, Robotics, and Cloud.