NVIDIA Deep Learning Institute Fundamentals Workshop for Computer Vision | SGInnovate
July 27
2018

Location

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.

 

Agenda:
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:

Isaac Ng

Isaac is a research engineer at the Smart Nation Translational Lab (SNTL) at Nanyang Technological University. SNTL is a research lab set up to leverage machine/deep learning and digital signal processing expertise to solve problems faced by government agencies in Singapore. Active projects in development include a noise classifier for reducing noise pollution for the Housing & Development Board (HDB) and an anomaly detection algorithm for improving the deployment of Singapore Civil Defence Force (SCDF) resources. He was previously a teaching assistant for control systems and computer science courses at the University of New South Wales. His passion is in condensing and disseminating complex concepts.

 

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]

Topics: Artificial Intelligence / Deep Learning / Machine Learning / Robotics

Upcoming Events

  • 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. 

    Topics:

    Blockchain

  • AI Readly

    This reading group is suited for AI researchers, academics and advanced practitioners to discuss top recent AI-related arXiv preprint papers. 

    Topics:

    Others

  • Google Next Billion Users (NBU): Tech, Trust and Safety in NBU Markets

    At this 5th edition, we will focus on Tech, Trust and Safety for NBU Markets. In NBU markets, users often face unique "cultural" challenges when it comes to access, content, community, privacy and safety. Discover why as we share insights from our team’s work in our NBU markets. Learn about the opportunities we have to create gender equitable, safer products, content programs, and marketing initiatives.

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • Lessons from Rising Global Markets

    With the world continuously on the move for innovation and growth, it causes the emergence of new markets. Just how do we keep up with the pace of rising global markets? Join us in a fireside chat as we discuss the exciting possibilities of emerging markets, and startup landscapes around the world.

    Topics:

    Others, Startups

  • Comet: SGInnovate’s Talent Networking Event

    At Comet, a select group of talent like yourself would be able to connect with Singapore’s forefront deep tech companies over one evening through a series of “speed-dating” conversations. Through these interactions, you could potentially find your next impactful role with companies in areas of AI, MedTech, robotics, energy and mobility solutions. 

    Topics:

    Talent

  • AgHack powered by Ministry of Data

    Aghack presents an opportunity for Singapore startups to access the Australian market and showcase their capabilities in building globally-relevant products at a regional level. SGInnovate is collaborating with the Ministry of Data (MoD) to facilitate and evaluate proposals from members of the Singapore startup community. 

    Topics:

    Data Science / Data Analytics

  • NexGen 2018 Singapore

    NexGen is a participative open innovation event that brings together leading companies, start-ups and aspiring students internationally to imagine the future together. Started in 2014 in Japan, this is the 2nd year that NexGen will be held in Singapore. Under the theme of "Smart Community", this year Tokyo Electric and Power Company (TEPCO) new technology arm TEPCO Ventures, and BC Technology Laboratory (BCTL) from Japan will present their challenge around energy infrastructure and blockchain for social good. Unique start-ups such as EntameCoin of Avex, Politics-Tech blockchain platform PoliPoli as well as motivated students from Japan, US and Singapore, together with the audience (i.e. YOU!) will then partiicipate in an interactive session and jointly innovate together.

    Topics:

    Blockchain, Investments, Startups

  • 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.

    Topics:

    Blockchain

  • AI for Earth: How AI Can Help Solve Earth’s Sustainability Challenges

    AI for Earth has one simple but huge ambition – to fundamentally transform the way one monitors, models and manages Earth’s natural resources using AI.  At the same time, deep learning innovations and breakthrough are happening both in academia and industry at a breathtaking pace.  By leveraging these AI innovations, and breakthroughs, many AI for Earth grantees have been using AI to solve many of earth’s toughest challenges -  ranging from precision agriculture, precision conservation to understanding and protecting biodiversity, and more.

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • The Future of Work Tackling Talent Shortage with Remote Teams

    More and more companies are looking for talent on a global level to power the digital transformation and employees are seeing the value and freedom of the digital nomad/remote work lifestyle. In this discussion we'll dive into practices of operating in different countries with teams of people working both remotely and in the office.

    Topics:

    Talent

  • Future of Energy: Building the Grid on the Blockchain

    Blockchain—the technology that underpins bitcoin and other cryptocurrencies—has the potential to remake important aspects of the energy industry. The emergence of blockchain introduces a new measure of uncertainty at a time when the industry is changing rapidly due to renewable and distributed energy, energy efficiency, energy storage, and digitization. Given their potential to streamline transactions and cut costs, blockchain could help to remove pain points and friction throughout the power value chain. 

    Topics:

    Blockchain

  • The Impact of Artificial Intelligence on Achieving the SDGs

    The Sustainable Development Goals (SDGs), otherwise known as the Global Goals, are a universal call to action to end poverty, protect the planet and ensure that all people enjoy peace and prosperity. Join us for this event and learn from the panel of experts how artificial intelligence can help to solve global challenges.

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • 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.

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • Sundown Networking: Robotics Technologies & Singapore

    Singapore is the second densest country with robots, having 488 robots per 10,000 employees. Coupled with abundant technical talent from engineers to computer scientists and S$19 billion committed in R&D over five years, the country is primed to take lead as a springboard for robotics technologies.

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • Morning Pitch Singapore: Food - Agri-Tech

    Morning Pitch is a pitching platform hosted by Deloitte Tohmatsu Venture Support. This platform helps start-ups form business alliances and partnerships with large corporations, corporate venture capital and venture capital firms. The focus on this Morning Pitch on 17 August 2018 is Food - Agri-Tech.

    Topics:

    Others, Startups

  • Angel Investing Workshop

    This course is brought to you by AngelCentral, as part of our mission to build a community of effective and competent angel investors in ASEAN.

    Topics:

    Investments

  • IBM Blockchain Foundation Developer Workshop

    Together with IBM, SGInnovate is bringing to you a Blockchain Foundation Developer Workshop, specifically designed for developers who want to acquire new skills or explore a career in Blockchain development.

    Topics:

    Blockchain

  • AngelCentral Deep Dive Series: Understanding Blockchain and Cryptocurrencies

    Have you been hearing this overused term, Blockchain and cryptocurrency repeatedly? Do you wish to know more, but don’t know how to get started on delving into it?

    Topics:

    Blockchain

  • Python for Beginners

    Explore the intersection of coding and data with General Assembly. During our Python-focused introductory workshop, you’ll learn to harness the power of an essential programming language for data scientists.

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • AI in Digital Health Past, Present and Future

    In health care, AI and related technologies (like machine learning) can be used to gain insight into a patient’s medical history, present state, and potential future outcomes. Healthcare companies supporting patients or providers will leverage AI to provide specific, personalized insights based on an individual’s current health status, lifestyle, behavior, and genetic information. Join our panel of experts for an evening exploring how data, AI and technology are redesigning healthcare.

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics, MedTech / HealthTech / BioTech

  • Combining Decision Optimization and Machine Learning To Improve Operational Efficiency

    In today's business environment, it is not uncommon to see in house data scientist teams with deep expertise in Machine Learning or an Operational Research team with skilled expertise in Decision Optimization. On its own, each method have a fair amount of success applying these technologies in isolation, how then can we combined both of these technologies to help them gain a competitive advantage?

    Topics:

    Artificial Intelligence / Deep Learning / Machine Learning / Robotics

  • Understanding Analytics Lifecycle and Start with Planning Analytics To Drive Performance Accelerators

    Many CFOs fears their organizations are not sufficiently prepared for the disruptive market trends, where one of their concerns which is not able to optimise their planning & budgeting and forecasting for their financial efficiency and business insights. In order to be "Performance accelerators", these organizations must leverage on (Analytics lifecycle) more extensively to plan for future and reduce risks.

    Topics:

    Others