Free

NVIDIA Deep Learning Institute Workshop @ University of Sydney - Day 2

Event Information

Share this event

Date and Time

Location

Location

Business School, ABS Collaborative Learning Studio 3190

Sydney University

Darlington Campus

Sydney, NSW 2006

Australia

View Map

Event description

Description

NVIDIA Deep Learning Institute, together with University of Sydney, is hosting a two day Accelerated Computing workshop:

Day 2 Deep Learning - comprising of lectures and hands-on labs, exclusively for vertifiable academic students, staff and researchers.

In this workshop, you will start with the basic concepts of deep learning and quickly move to learning how to solve real-world problems using neural networks.

NVIDIA Deep Learning Institute Certified Instructors will blend lecture and hands-on, real-world exercises to explore how to solve the most challenging problems with deep learning.

Attendees must bring their own laptops and power supply. Connectivity will be through the University Wi-Fi.

You will learn to:

  • Understand general terms and background of deep learning
  • Leverage deep neural networks (DNN) with the DL workflow to solve a real-world image classification problem
  • Train and evaluate an image segmentation network using TensorFlow


Agenda - Day 2 (February 27)

09:00 Registration

09:15 Deep Learning Demystified (lecture)

10:00 Image Classification with DIGITS (hands-on lab)

12:00 Lunch

13:00 Image Segmentation with TensorFlow (hands-on lab)

15:00 Break

15:10 Neural Network Deployment with TensorRT (hands-on lab)

17:00 Running GPU jobs on the USYD Artemis HPC (The University of Sydney)


Content Level: Beginner

Pre-requisite:

  • Basic C/Python understanding can be helpful for some exercises
  • No background in deep learning is required for this training
  • The mathematical and theoretical aspects of deep learning will NOT be covered by this training - and they're not a requirement to complete the labs, reading the Wikipedia page of Deep Learning would be a good start if you're interested.


IMPORTANT: To reserve your seat, you MUST register at with a valid university email address and follow these pre-workshop instructions.

  • You must bring your own laptop, charger and adaptor (if needed) to this workshop.
  • Please note that access to the same email address used to register for the event on Eventbrite, will be required for the Qwiklabs account registration on the event day - which is used to run the hands-on labs. Please ensure you use only your university email address only.


Training Syllabus - Day 2

DLI Lab #1: Image Classification with DIGITS

Learn how to leverage deep neural networks (DNN) within the deep learning workflow to solve a real-world image classification problem using NVIDIA DIGITS. You’ll walk through the process of data preparation, model definition, model training and troubleshooting, validation testing and strategies for improving model performance using GPUs. On completion of this lab, you will be able to use NVIDIA DIGITS to train a DNN on your own image classification application.

DLI Lab #2: Image Segmentation with TensorFlow

There are a variety of important applications that need to go beyond detecting individual objects within an image and instead segment the image into spatial regions of interest. Examples of image segmentation uses include medical imagery analysis where it is often important to separate the pixels corresponding to different types of tissue, blood or abnormal cells so we can isolate a particular organ and self-driving cars where it is used to understand road scenes. In this lab you’ll learn how to train and evaluate an image segmentation network.

Running GPU jobs on the USYD Artemis HPC (The University of Sydney):

This session will explain how to connect to the HPC cluster and V100s GPUs based in the University of Sydney.

NVIDIA Experts:

Nicolas Walker

Nicolas Walker is a Senior Solution Architect at NVIDIA. He supports customers in South East Asia developing data center and workstation solutions in the areas of High Performance Computing, Deep Learning, Virtualized Desktops and Professional Graphics. Before joining NVIDIA in February 2016, Nicolas held roles in IBM and Lenovo as solution architect focusing on enterprise infrastructure and HPC for the last 15 years. Before moving to Singapore, he was based in Italy, Scotland and Malaysia. He holds a BSc(Hons) in Software Engineering.

Maggie Zhang

Maggie Zhang is a Solutions Architect in the areas of HPC/DL at NVIDIA, ANZ. Before joining NVIDIA, she worked as a postdoctoral researcher in Lero (The Irish Software Research Center), Ireland and a research fellow in National University of Defense Technology, China. Her research areas are GPU/CPU heterogeneous computing, compiler optimization, computer architecture, deep learning. She got her PhD in Computer Science & Engineering from the University of New South Wales in 2013.

Michael Lang

Michael Lang has been active in the virtualization and VDI spaces for well over a decade, as a partner, vendor and always as an advocate for improved business outcomes. Whether it is with a mining, government or defense customer, or an architectural firm looking to solve challenges or increase productivity, he brings a wealth of knowledge and experience to benefit his customers. In addition, he is the Intelligent Video Analytics Solutions architect for Deep Learning based solutions at NVIDIA ANZ. Michael is an NVIDIA Certified Deep Learning Instructor, and holds multiple technical certifications, has a Masters in IT Security, and degrees in Psychology and Philosophy.

Share with friends

Date and Time

Location

Business School, ABS Collaborative Learning Studio 3190

Sydney University

Darlington Campus

Sydney, NSW 2006

Australia

View Map

Save This Event

Event Saved