Deep Learning Jump-Start Workshop | SGInnovate
July 12-13
2018

Location

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

Deep Learning Jump-Start Workshop

Presented by SGInnovate and Red Dragon AI

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.

This workshop gives participants a grounded understanding of how Deep Learning works and how to start applying it straight away for their own unique projects.

The workshop consists of a 2 full days session from Thursday to Friday, 12 to 13 July 2018 and is eligible for funding support.

Attendees MUST bring their own laptops

Workshop Overview:
In the course participants will learn:

  • The basic concepts Neural Networks and an introduction to the mathematics of Deep Learning
  • They will be introduced to the Keras API and how it works as a higher level of abstraction for TensorFlow
  • Building and using TensorFlow native Estimators
  • Building various types of Deep Learning models
  • Building models for Computer Vision challenges
  • Building models for Natural language challenges

The course will consist of 2 full days from 845am to 530pm with lunch and 2 tea breaks provided.

Once participants have an understanding of the basics, they will proceed to work on their own models and projects.

The following day includes looking at more advanced uses of Deep Learning for Computer Vision and for Natural Language Processing and allow for students to ask questions about their own projects.

Agenda:

Day 1 – Thurs, 12 Jul 
08:45 Registration
09:15 The Key Concepts behind Deep Learning and Introduction to the basic math
10:45 Tea Break
11:00 Building your first Neural Network
12:30 Lunch
13:30 Building a Convolutional Neural Network
15:00 Tea Break
15:15 Using Transfer Learning for new problems
16:15 Doing a Project
17:15 Closing Comments and Questions

Day 2 – Fri, 13 Jul
08:45 Registration
09:00 Deep Learning for Natural Language Processing
11:00 Project Clinic 1

12:30 Lunch
13:30 Deep Learning for Computer Vision 
14:30 Building a Model for Structured Data with TensorFlow Estimators
15:30 Project Clinic 2
16:30 Closing Comments and Questions

 

Day 1, Section 1: The Key Concepts behind Deep Learning and Introduction to the basic math
A simple introduction to how the math behind networks works

  • Math of Neural Networks and Back Propagation
  • Activation functions
  • Loss functions
  • Optimization functions

Day 1, Section 2: Building your first Neural Network
Frameworks:
TensorFlow, Keras
A look into the Keras API

  • Parts of a Model
  • Hidden Layers in action
  • Keras Layers API
  • Multi-Layer Perceptrons 
  • Setting Hyperparamaters

Day 1, Section 3: Building a Convolutional Neural Network
Frameworks:
TensorFlow, Keras
Convolutional Model Architectures

  • Convolution layers
  • Pooling layers
  • Dropout and how it effects networks
  • Combining Convolution layers

Day 1, Section 4: Using Transfer Learning for new problems
Frameworks:
TensorFlow, Keras
Understanding the Estimator framework and its advantages

  • Inception Network
  • Building a classifier with a pre-trained network
  • Reusing and retraining weights for a specific task

Day 1, Section 5: Doing a Project
Frameworks:
TensorFlow, Keras
Actually *doing something* is very important

  • Ideas for projects to do
  • Q&A on ‘doable projects’
  • Homework: What to bring to the next session

Day 2, Section 6: Deep Learning for Natural Language Processing Evening Session
Frameworks:
TensorFlow, Keras, Estimators
Using Deep Learning for problems related to language

  • Ways to represent words and language
  • Intro to RNNs
  • Classifying Text
  • Project questions and general follow up

Day 2 Session 1, Project Clinic 1

Day 2 Session 2, Section 7: Deep Learning for Computer Vision Evening Session
Frameworks:
TensorFlow, Keras, Estimators
Various types of Computer vision tasks

  • Understanding more advance image networks
  • Generative modelling for images
  • Examples of Style Transfer and Deep Dream

Day 2, Section 8: Building a Model for Structured Data with TensorFlow Estimators
Frameworks:
TensorFlow, Estimators, Datasets API
Understanding the Estimator framework and its advantages

  • What makes up an Estimator 
  • Canned Estimator
  • Building a network for Structured Data
  • Estimator Input function
  • Intro to the TensorFlow Datasets API

Day 2, Project Clinic 2

 

Recommended Prerequisites

  • An interest in Deep Learning
  • Ability to be able to read and follow code
  • We will send out some videos to help people with Python syntax specifically before the course begins.

 

Instructors' Biodata
Dr Martin Andrews
Martin has over 20 years experience in Machine Learning and using it to solve problems in financial modeling and creating AI automation for companies. His current area of focus and specialty is in natural language processing and understanding. In 2017 Google appointed Martin one of the first 12 Google Developer Experts for Machine Learning.

Sam Witteveen
Sam has used Machine Learning and Deep Learning in building multiple tech startups, including a children’s educational app provider which has over 4 million users worldwide. His current focus is AI for conversational agents to allow humans to interact easier and faster with computers. In 2017 Google appointed Sam one of the first 12 Google Developer Experts for Machine Learning in the world.

 

Funding Support
This workshop is eligible for e2i and UTAP Funding Support schemes.

e2i
An initiative of the National Trades Union Congress (NTUC), e2i (Employment and Employability Institute) supports nation-wide manpower and skills upgrading programmes.

Criteria for e2i Funding Support eligibility:

  • participant must be a Singaporean or a Singapore Permanent Resident
  • company-sponsored participant must not be from a Public Agency (includes but not limited to Ministries, Statutory Boards, Organisation of State, etc)
  • achieves 100% workshop attendance
  • must complete & submit a survey form after the online registration to fulfil funding requirements

* Note: e2i Funding is on a reimbursement basis and refund processing may take up to 2 months after course completion. Participants who do not fulfil ANY of the above criteria will NOT be eligible for e2i funding.


UTAP
Union Training Assistance Programme (UTAP) is an individual skill upgrading account for NTUC members. As a member, you will enjoy UTAP funding up to 50% of the unfunded^ course fee, capped at $250 every year.  
 (^Unfunded course fee refers to the balance course fee payable after applicable government subsidy. This excludes GST, registration fees, misc. fees etc.)

Criteria for UTAP Funding Support eligibility:

  • participant must have paid-up union membership before course commencement, throughout whole course duration and at the point of claim
  • course must not be funded through company sponsorship or other types of funding 
  • achieves 100% workshop attendance
  • UTAP self-application must be submitted within 6 months after course completion 

* Note: UTAP Funding is on a reimbursement basis and payment processing may take up to 2 months upon your successful self-application after the workshop ends. Participants who do not fulfil ANY of the above criteria will NOT be eligible for UTAP funding.

To apply for UTAP Funding,
Please submit an online application within 6 months after the workshop ends: https://www.ntuc.org.sg/wps/portal/up2/home/eserviceslanding?id=6bc1ca2c-ce81-4acb-a28f-c0be586e185f 

UTAP Step-by-Step Application Guide: 
http://demo.e2i.com.sg/wp-content/uploads/2017/05/UTAP-Step-by-Step-Application-Guide_Apr2017.pdf 

For more information on UTAP, please visit http://skillsupgrade.ntuc.org.sg / email [email protected]  / call the NTUC Membership hotline at 6213 8008.

Summary of Funding Support Eligibility

Supported by

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. 

  • 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. 

  • 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.  

  • 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. 

  • 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. 

  • NVIDIA Deep Learning Institute Fundamentals Workshop for Computer Vision

    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.