2 Mar 2019

XENON NVIDIA Multiple Data Types Workshop

The NVIDIA Institute (DLI) and XENON invite you to attend the Fundamentals of Deep Learning – Multiple Data Types hands-on workshop on:

Thursday April 11th
9:00am – 5:00pm
Monash University – Seminar 1,
Level 7, 30 Collins St Melbourne VIC 3000

Early bird

ONLY $395 inc GST for bookings made by the 30th March 2019

General Admission

$550 inc GST

About This Workshop

This workshop explores how convolution and recurrent neural networks can be combined to generate effective descriptions of content within images and video clips.

Learn how to train a network using TensorFlow and the Microsoft Common Objects in Context (COCO) dataset to generate captions from images and video by:

  • Implementing Deep Learning workflows like image segmentation and text generation
  • Comparing and contrasting data types, workflows, and frameworks
  • Combining computer vision and natural language processing

Upon completion, you’ll be able to solve problems that require multiple types of data inputs. You will receive a Fundamentals certificate from Institute!

Attendees MUST bring their own laptops.

Workshop Agenda

09:00 Registration
09:30 Image Segmentation with TensorFlow (hands-on lab)
11:00 Tea Break
11:15 Word Generation with TensorFlow (hands-on lab)
12:30 Lunch
13:30 Word Generation with TensorFlow (hands-on lab) [continued]
14:45 Image and Video Captioning by Combining CNNs and RNNs (hands-on lab)
15:45 Tea Break
16:00 Image and Video Captioning by Combining CNNs and RNNs (hands-on lab) [continued]
17:00 Closing Comments and Questions

Lunch and Coffee provided by XENON

Prerequisites

Familiarity with basic Python (functions and variables) and prior experience training neural networks is expected.

XENON Titus Tang Workshop

Instructor: Titus Tang

Titus Tang is a Deep Learning consultant at Alpha One AI and a lecturer and tutor at Monash University, sharing his knowledge in the areas of AI, computer systems and software engineering. He is also the founder of Monash Deep Learning Workshops.

Titus completed a Ph.D. in computer vision and 3D sensing at Monash University with the Monash Vision Group. Advised by Dr. Wai Ho Li and Prof. Tom Drummond.

 

DETAILED COURSE OUTLINE

Components Description
Introduction
  • Course Overview
  • Getting Started with
Introduction to , situations in which it is useful, key terminology, industry trends, and challenges.
Image Segmentation with TensorFlow
  • Compare image segmentation to other computer vision problems
  • Experiment with TensorFlow tools
  • Implement effective metrics for assessing model performance
Hands-on exercise: Segment MRI images to measure parts of the heart using tools such as TensorBoard and the TensorFlow Python API.
Word Generation with TensorFlow
  • Introduction to Natural Language Processing (NLP) and Recurrent Neural Networks (RNNs)
  • Create network inputs from text data
  • Test with new data
  • Iterate to improve performance
Hands-on exercise: a Recurrent Neural Network to understand both images and text, and to predict the next word of a sentence using the MSCOCO (Microsoft Common Objects in Context) dataset.
Image and Video Captioning
  • Combine computer vision and natural language processing to describe scenes
  • Learn to harness the functionality of Convolutional Neural Networks
    (CNNs) and RNNs
Hands-on exercise: Train a model that generates a description of an image from raw pixel data by combining outputs of multiple networks (CNNs and RNNs) through concatenation and/or averaging.
Summary
  • Summary of Key Learnings
  • Workshop Survey
Review of concepts and practical takeaways.

 

Workshop Setup Instructions:

  1. Create an NVIDIA Developer account at http://courses.nvidia.com/join.
  2. Make sure that WebSockets works for you:
    • Test your laptop at http://websocketstest.com
    • Under ENVIRONMENT, confirm that “WebSockets” is checked yes.
    • Under WEBSOCKETS (PORT 80), confirm that “Data Receive,” “Send,” and “Echo Test” are checked yes.
  3. If there are issues with WebSockets, try updating your browser. We recommend Chrome, Firefox, or Safari for an optimal performance.
  4. Once onsite, visit http://courses.nvidia.com/dli-event and enter the event code provided by the instructor.

This workshop is brought to you by:

XENON Systems logo XENON NVIDIA logo