Deep Learning Jumpstart Workshop (13 – 14 November 2019)

Overview

Together with Red Dragon AI, SGInnovate is pleased to present the Deep Learning Developer Series. The Jumpstart workshop is the first module of the Deep Learning Developer Series and it is a prerequisite to the advanced Deep Learning modules.

This two-day workshop is designed to introduce you the skills needed to start your journey as a Deep Learning Developer. It goes through the overall concepts and techniques for building a variety of Deep Learning models for tabular data, image data, audio data and text data.

At the end of the classroom training, you will work on your models and projects. Additional learning materials and assessments will be available online, with one-on-one sessions for you to ask questions on your project. This is especially useful for understanding how to apply these skills for your unique applications.

By the end of the workshop, you will be able to take your new-found Deep Learning knowledge and apply it to your job or projects straight away!

This Deep Learning Developer Series is a hands-on series targeted at developers and Data Scientists who are looking to build Artificial Intelligence (AI) applications for real-world usage. It is an expanded curriculum that breaks away from the regular eight-week full-time course structure and allows modular customisation according to your own pace and preference.

The curriculum will cover many of the fundamentals needed in Deep Learning projects, as well as models such as Fully Connected Neural Networks, Convolutional Neural Networks and Recurrent Neural Networks. Real-world examples will be used to identify the best techniques to tackle various data science problems at hand.

This workshop is eligible for funding support. For more details, please refer to the "Pricing" tab above.

In this course, participants will learn:

• The basic concepts of Neural Networks and an introduction to the mathematics of Deep Learning
• An introduction to the Keras API and how it works as a higher level of abstraction for TensorFlow
• To build and use TensorFlow native estimators
• To build various types of Deep Learning models
• To build models for Computer Vision challenges
• To build models for Natural Language challenges

Prerequisites:

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

Pre-Workshop Instructions:

• You MUST bring your laptop to this workshop
• Please watch the introductory videos that will be sent out separately
• Please experiment with the pre-exercises given

Agenda

Day 1 (13 November 2019)

08:45am – 09:00am: Registration
09:00am – 10:45am: Key Concepts behind Deep Learning and Introduction to the basic math
A simple introduction to how math behind networks works

• What is Deep Learning and examples of Deep Learning in Industry 
• Math of Neural Networks and Back Propagation
• Activation functions
• Loss functions
• Optimisation functions

10:45am – 11:00am: Tea Break
11:00am – 12:30pm: 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 Hyperparameters

12:30pm – 1:30pm: Lunch
1:30pm – 3:00pm: Building a Convolutional Neural Network (CNN)
Frameworks: TensorFlow, Keras - Convolutional Model Architectures

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

3:00pm – 3:15pm: Tea Break
3:15pm – 4:45pm: Using Transfer Learning for new problems
Frameworks: TensorFlow, Keras - Understanding the TensorFlow ecosystem and its advantages

• Inception Network
• VGG16
• Building a classifier with a pre-trained network
• Reusing and retraining weights for a specific task

4:45pm – 5:15pm: Doing a Project
Frameworks: TensorFlow, Keras - Actually *doing something* is very important

• Ideas for projects to work on
• Q&A on projects
• Homework: What to bring for the next session

5:15pm – 5:30pm: Closing comments and questions

Day 2 (14 November 2019)

8:45am – 9:00am: Registration
9:00am – 10:45am: Deep Learning for Natural Language Processing
Frameworks: TensorFlow, Keras, Estimators - Using Deep Learning for problems related to language 

• Ways to represent words and language
• Intro to Recurrent Neural Networks (RNNs)
• Using RNNs on character models 
• Classifying Text
• Project questions and general follow up

10:45am – 11:00am: Tea Break

11:00am – 12:30pm: Project Clinic 1
Project questions and general follow up

12:30pm – 1:30pm: Lunch

1:30pm – 2:30pm: Deep Learning for Computer Vision
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

2:30pm – 3:15pm: Building a Model for Structured Data with TensorFlow estimators
Frameworks: TensorFlow, Estimators, Datasets API - Understanding the Estimator framework and its advantages

• How does TensorFlow fit the APIs together into an end to end system
• Building input pipelines
• Building a network for Structured Data
• Using tf.Data for pipelines
• Intro to the TensorFlow Datasets API

3:15pm – 3:30pm: Tea Break

3:30pm – 4:30pm: Project Clinic 2

Project questions and general follow up

4:30pm – 5:00pm: Closing comments and questions

You will be given two weeks to complete your online learning and individual project. 

Online Learning (9.5 hours)

• Python Basics
• Colabs and Notebooks
• Neural Network Basics
• Keras Basics
• CNNs
• RNNs
• TensorFlow Estimators
• Preprocessing Patterns
• Project Walkthroughs
• Cloud Training

Assessments:

You must fulfil the criteria stated below to pass and complete the course.

1.    Online Tests: Participants are required to score an average grade of more than 75% correct answers to the online questions.

2.    Project: Participants are required to present a project that demonstrates the following:

• The ability to use or create a data processing pipeline that gets data in the correct format for running in a Deep Learning model
• The ability to create a model from scratch or use transfer learning to create a Deep Learning model
• The ability to train that model and get results
• The ability to evaluate the model on held out data

Pricing

Funding Support

This workshop is eligible for CITREP+ funding.

CITREP+ is a programme under the TechSkills Accelerator (TeSA) – an initiative of SkillsFuture, driven by Infocomm Media Development Authority (IMDA).

*Please see the section below on ‘Guide for CITREP+ funding eligibility and self-application process’

Funding Amount: 

• CITREP+ covers up to 90% of your nett payable course fee depending on eligibility for professionals

Please note: funding is capped at $3,000 per course application

• CITREP+ covers up to 100% funding of your nett payable course fee for eligible students / full-time National Servicemen (NSF)

Please note: funding is capped at $2,500 per course application

Funding Eligibility: 

• Singaporean / PR
• Meets course admission criteria
• Sponsoring organisation must be registered or incorporated in Singapore (only for individuals sponsored by organisations)

Please note: 

• Employees of local government agencies and Institutes of Higher Learning (IHLs) will qualify for CITREP+ under the self-sponsored category
• Sponsoring SMEs organisation who wish to apply for up to 90% funding support for course must meet SME status as defined here

Claim Conditions: 

• Meet the minimum attendance (75%)
• Complete and pass all assessments and / or projects

Guide for CITREP+ funding eligibility and self-application process:

• Individuals (Self-Sponsored)
• Organisation-Sponsored
• Students / NSF

For more information on CITREP+ eligibility criteria and application procedure, please click here. 

In partnership with:

Driven by:

For enquiries, please send an email to learning@sginnovate.com

Trainer

Dr Martin Andrews
Martin has over 20 years’ experience in Machine Learning and has used it to solve problems in financial modelling and has created AI automation for companies. His current area of focus and speciality is in natural language processing and understanding. In 2017, Google appointed Martin as one of the first 12 Google Developer Experts for Machine Learning. Martin is also one of the co-founders of Red Dragon AI. 

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