NVIDIA Deep Learning Institute Fundamentals Workshop for Computer Vision | SGInnovate
July 27


Perl @ BASH, Level 3
79 Ayer Rajah Crescent
Singapore 139955

NVIDIA Deep Learning Institute Fundamentals Workshop for Computer Vision

Presented by NVIDIA, SGInnovate and National Supercomputing Centre

SGInnovate partners with NVIDIA Deep Learning Institute (DLI) to offer hands-on training to developers, data scientists, and researchers looking to solve real world problems with deep learning across diverse industries such as self-driving cars, healthcare, online services and robotics.

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

You will receive a Fundamentals certificate from Deep Learning Institute!

Attendees MUST bring their own laptops

Workshop Overview:

This full-day workshop covers the foundations of deep learning and offers hands-on training in Image Classification, Object Detection, and Neural Network Deployment using popular frameworks.

You will learn to:

  • Understand basic of deep learning by training and deploying neural networks. 
  • Implement common deep learning workflows, such as image classification and object detection.
  • Experiment with data, training parameters, network structure, and other strategies to increase performance and capability.
  • Deploy your neural networks to start solving real-world problems.

Upon completion, you’ll be able to start solving problems on your own with deep learning.


Recommended Pre-requisites:

  • No background in deep learning is required for this training
  • Basic python understanding can be useful for some exercises
  • 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.


08:45 Registration
09:15 Deep Learning Demystified (lecture)
10:00 Break
10:15 Image Classification with DIGITS (hands-on lab)
12:30 Lunch
13:30 Approaches to Object Detection with DIGITS (hands-on lab)
15:15 Tea Break
15:30 Neural Network Deployment with TensorRT (hands-on lab)
16:45 Closing Comments and Questions
17:00 End

Lab #1: Image Classification with DIGITS
Deep learning enables entirely new solutions by replacing hand-coded instructions with models learned from examples. Train a deep neural network to recognize handwritten digits by:

  • Loading image data to a training environment 
  • Choosing and training a network
  • Testing with new data and iterating to improve performance 

On completion of this Lab, you will be able to assess what data you should be training from.

Lab #2: Object Detection with DIGITS
Many problems have established deep learning solutions, but sometimes the problem that you want to solve does not. Learn to create custom solutions through the challenge of detecting whale faces from aerial images by:

  • Combining traditional computer vision with deep learning 
  • Performing minor “brain surgery” on an existing neural network using the deep learning framework Caffe
  • Harnessing the knowledge of the deep learning community by identifying and using a purpose-built network and end-to-end labeled data.

Upon completion of this lab, you will be able to solve custom problems with deep learning.

Lab #3: Neural Network Deployment with DIGITS and TensorRT
Deep learning allows us to map inputs to outputs that are extremely computationally intense. Learn to deploy deep learning to applications that recognize images and detect pedestrians in real time by:

  • Accessing and understanding the files that make up a trained model 
  • Building from each function’s unique input and output
  • Optimizing the most computationally intense parts of your application for different performance metrics like throughput and latency 

Upon completion of this Lab, you will be able to implement deep learning to solve problems in the real world.


Instructors’ Biodata:

Nicholas Capel

Nicholas is the Chief Scientist of Adaline.io, a deep learning startup involved in the field of pathology and radiology. 
He completed his Master of Engineering in Information and Computer Engineering from the University of Cambridge in the United Kingdom. He has worked as a full stack developer in TripAdvisor in Oxford, and as an engineer in StarLeaf with a focus on video compression. 


DLI Attendees Pre-Workshop Instructions

  1. You MUST bring your own laptop to this workshop.
  2. Create an account by going to https://nvlabs.qwiklab.com/ prior to getting to the workshop.
  3. MAKE SURE your laptop is set up prior to the workshop by following these steps:
    • Ensure websockets runs smoothly on your laptop by going to http://websocketstest.com/ 
    • Make sure that WebSockets work for you by seeing under Environment, WebSockets is supported and Data Receive, Send and Echo Test all check Yes under WebSockets (Port 80).
    • If there are issues with WebSockets, try updating your browser or trying a different browser. The labs will not run without WebSockets support.
    • Best browsers for the labs are Chrome, FireFox and Safari. The labs will run in IE but it is not an optimal experience.
  4. Please remember to sign in to https://nvlabs.qwiklab.com/ using the same email address as for event registration, since class access is given based on the event registration list.

For enquiries, please send an email to [email protected]

Upcoming Events

  • CrossCTF 2018

    Singapore has an increasing demand for information security professionals and to keep up to that demand, there is the need to constantly search for talents in the field or to nurture new people.

  • Machine Learning Using Python

    This two day workshop will introduce students to data exploration and machine learning techniques. Students will learn about the data science workflow and will practice exploring and visualising data using Python and built-in libraries. Students will also explore the differences between supervised and unsupervised learning techniques and practice creating predictive regression models.

  • Google Next Billion Users (NBU): Android and Data Best Practices for NBU Markets

    At this 4th edition, we will focus on Android and data best practices for NBU markets. Building apps for Next Billion Users is quite different. Users in merging markets have unique needs, culture, environment and technological constraints. We are going to talk about the best practices in building Android apps in terms of connectivity, compatibility, performance and client/server communication.

  • AI Readly

    This reading group is suited for AI researchers, academics and advanced practitioners. We meet every Tuesday, 7:00pm - 9:00pm at BASH, Level 3, Block 79 Ayer Rajah Crescent (part of JTC [email protected]-North) to discuss top recent AI-related arXiv preprint papers. 

  • ScaleUp with SGInnovate-Microsoft Startup Pitching

    Join us on our pitching day on 19-June-2018 as a specially selected group of startups pitch in front of a distinguished panel of judges to vie for 2 spots to pitch to the global Microsoft ScaleUp Programme’s final selection committee (at a global venue, with date and time to be confirmed), designed for the top 10-20 Series A startups in the world.

  • AI & The Future of Money

    The world of finance is rapidly evolving. Today, there are new ways to pay, lend, invest, and conduct almost every type of financial transaction. And the pace of innovation is not slowing down, in fact, it's picking up.

  • AI Evening: Delivering Deep Learning in Enterprise, Setting Up Engineering Backbone Processes

    Join SGInnovate and IBM on 21 June as we explore how to instill deep learning as an engineering process in enterprises. While the science is becoming accessible, practicing it in a repeatable and measurable enterprise discipline remain hard.

  • Fundamentals of Deep Learning Workshop for Multiple Data Types

    SGInnovate partners with NVIDIA Deep Learning Institute (DLI) to offer hands-on training to developers, data scientists, and researchers looking to solve real world problems with deep learning across diverse industries such as self-driving cars, healthcare, online services and robotics.

  • BlockFellows Singapore Hub

    BlockFellows is a community initiative by TokenScore to train up more blockchain experts and competent blockchain programmers for free. We are partnering with Indorse and SGInnovate to run the Singapore Hub of BlockFellows, with weekly meetups for the Advanced Blockchain Programming fellowship running for 15 weeks, led by volunteer expert mentors.

  • Deep Tech Stories: Australia and Singapore

    Date: 25 June 2018
    Time: 5:30pm – 7:30pm
    Venue: BASH, 79 Ayer Rajah Crescent, #03-01, Singapore 139955

  • New Tech and Energy Companies of the Future

    The session will focus on the intersection of new tech and energy companies of the future, which will be distributed and running on a digital backbone. We will discuss what are the different technology solutions and what are the capabilities they bring and how they will change the business models.

  • Technology & Society: Innovation for Social Impact

    This event brings together technologists, change makers, impact investors, social innovators and impact accelerators on a single panel for an engaging discussion around the topics of innovation for social impact. 

  • The Appier Story: Building an AI Startup from the Ground Up

    At this first Appier AI Masterclass, Appier’s CEO and Co-Founder Chih-han Yu will share his own journey in AI and how together with a few friends, they decided to start a company to realise their vision for how AI can contribute to society.

  • Blockchain 3.0 - Future Decentralized

    The first version of blockchain of bitcoin blockchain focuses on peer-to-peer money transfer. As blockchain technology evolved from this version 1.0, Ethereum has emerged as version 2.0 allowing decentralised apps to be built on top of it. Version 3.0 promises to be highly scalable with millions of transactions running on it with the aim of allowing real world complex applications to run atop. Join us as we explore how MorpheusLabs together with Quarkchain bring this idea to live.

  • AngelCentral Pitch Day

    Join us as our curated pool of startups pitches to our community of angel investors to raise funds for their business. During the session, we will also be sharing about what AngelCentral does to support the angel investment scene in Southeast Asia. 

  • Design a T-shirt: Think Geek, Think Deep

    Passionate about STEM and want to be part of the rapidly growing science & technology community? Here is your chance! Whether you are a designer, coder or engineer by training, let your creative juices flow - YOU can show how cool deep technology is by designing a t-shirt that is uniquely coded.

  • Bluzelle Phase 2: Building the New Data Economy

    Data is now a new currency. Apps and devices exchange massive amounts of data; companies like Facebook abuse and sell your data; centralised structures are leading to more and more data breaches.

  • Blockchain Programming for Programmers – Session 7

    This is a hands-on event - please come with laptops. We will be programming. At the end of the session, you should have working code. 

  • Live With AI: Understanding Human Needs Amidst the Rise of Artificial Intelligence

    Live with AI’s key board members will present their research on the positive impact AI will bring to our society and business and highlight key recommendations to better live with AI. 

  • How AI Improves Customer Experience and Employee Productivity

    AI-powered chatbots, when connected to deep customer data, can deliver powerful new customer service experiences and help service organisations scale at a low cost. Join us to gain insights on how leading corporations and organisations are using Einstein Bots, using AI to deliver the future of customer service, to help customers get to answers faster in a personalised way. We will discuss how you can get your service organisations ready for working with bots and best practices for implementing Einstein Bots to reduce time and effort for both your customers and agents.  

  • Blockchain in Art: Authentication & Provenance

    Provenance Tracking is a blockchain powered tagging solution developed by LuxTag for Poesy Liang. It utilizes the NEM Blockchain Technology, offering smart contracts and multi-signature features. The project has the purpose of recording the provenance history of every piece of art. 

  • Technology That Matters: Epi-everything: Convergent Technologies Yield New Opportunities Beyond the Genome

    Humans are defined by the set of ~20,000 genes that comprise the genome, which is often viewed as a human parts list – the “what” of molecular biology. The central dogma of molecular biology then describes “how” these genes are expressed: they are transcribed into messenger RNAs that are translated into proteins.  But it says nothing about the “when” or “how much” of gene expression. 

  • Deep Learning Jump-Start Workshop

    SGInnovate partners with Red Dragon AI to offer hands-on, cutting-edge training to developers and data scientists who are looking to build AI Applications for real world use.

  • Startup Stories: Deep Tech Built from Singapore for the World

    Forget metrics like Gross Merchandise Value, Conversions and Traffic Growth. The founders and senior executives of Deep Technology companies in Singapore, covering the fields of space tech, medtech, autonomous vehicles, show how their companies offer a direct benefit to the environment, healthcare and urban planning. Learn how DeepTech is changing the world — for the better.

  • Blockchain Programming for Programmers – Session 8

    This is a hands-on event - please come with laptops. We will be programming. At the end of the session, you should have working code.