Foundations of Deep Learning | SGInnovate

DATE: TBC

Location

TBC

Foundations of Deep Learning

Organised by SGInnovate and Red Dragon AI

Together with Red Dragon AI, SGInnovate is pleased to present the Deep Learning Developer Series. Formerly known as the Deep Learning Jumpstart workshop, the Foundations of Deep Learning workshop is the first module of the Deep Learning Developer Series. This three-day online workshop is designed to introduce you to the skills needed to start your journey as a Deep Learning Developer. By the end of the workshop, expect to be empowered with the ability to take your newfound Deep Learning knowledge and apply it to your job / 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 Foundations of Deep Learning Workshop is a prerequisite to the advanced Deep Learning Developer modules. It goes through both the overall concepts and techniques for not only understanding, but building a variety of Deep Learning models for tabular data, image data, audio data and text data.

Start here

    • Have an interest in Deep Learning?
    • Join us if you are able to read and follow codes
    • This module is compulsory before you take the advanced modules
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 AND module 2 OR 3 before this module
     
    • You will need to take module 1, 2 AND 3 before this module
    • Attain a “Deep Learning Specialist” certification when you complete all five modules
     
    • Have an interest in Deep Learning?
    • Join us if you are able to read and follow codes
    • This module is compulsory before you take the advanced modules
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 AND module 2 OR 3 before this module
     
    • You will need to take module 1, 2 AND 3 before this module
    • Attain a “Deep Learning Specialist” certification when you complete all five modules
     

The curriculum will cover many of the fundamentals needed in Deep Learning projects, the TensorFlow ecosystem, as well as models tackling Computer Vision and Natural Language challenges. Real-world examples will be used to identify the best techniques to tackle various data science problems at hand.

Apart from learning Deep Learning techniques, you will apply them to a project of your choice. The goal is to empower you with the ability to apply your newfound Deep Learning knowledge to your job / projects right away.

The course will be conducted online. Participants will have an understanding of the basics during the course, and will work on their own models and projects individually. There will also be a follow up online learning session with learning materials and assessments provided. This is especially useful for understanding how to apply these skills for your unique applications.

Workshop Overview:

In this course, participants will learn:

  • The basic concepts of Neural Networks and an introduction to the mathematics of Deep Learning
  • The TensorFlow Keras API and how it works as a higher level of abstraction for TensorFlow
  • Building various types of Deep Learning models
  • Building models using various TensorFlow APIs and the TensorFlow ecosystem
  • Building models for Computer Vision challenges
  • Building models for Natural language challenges
  • How to use an Object Detection model
  • How to use a Bidirectional Encoder Representations from Transformers (BERT) model for Text Classification

Recommended 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

The course comprises of a 3-day online workshop, e-learning modules & individual project work.

Day 1

Section 1: The Key Concepts behind Deep Learning and Introduction to the basic math
Frameworks: None
Abstract: A simple introduction to how the math behind networks work
-    What is Deep Learning and examples of Deep Learning in Industry 
-    Math of Neural Networks and Back Propagation
-    Activation functions
-    Loss functions
-    Optimisation functions

Section 2: Building your first Neural Network
Frameworks: TensorFlow, Keras
Abstract: A look into the Keras API
-    Parts of a Model
-    Hidden Layers in action
-    Keras Layers API
-    Multi-Layer Perceptrons 
-    Setting Hyperparameters

Section 3: Building a Convolutional Neural Network
Frameworks: TensorFlow, Keras
Abstract: Convolutional Model Architectures
-    Convolution layers
-    Pooling layers
-    Dropout and how it affects networks
-    Combining Convolution layers 

Day 2

Section 4: Using Transfer Learning for new problems
Frameworks: TensorFlow, Keras
Abstract: 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

Section 5: Project
Frameworks: TensorFlow, Keras
Abstract: Actually *doing something* is very important
-    Ideas for projects to do
-    Q&A on ‘doable projects’
-    Homework: What to bring to the next session

Section 6: Deep Learning For Natural Language Processing 
Frameworks: TensorFlow, Keras
Abstract: Using Deep Learning for problems related to language
-    Ways to represent words and language
-    Intro to RNNs
-    Using Recurrent Neural Networks on character models 
-    Classifying Text
-    Project questions and general follow up

Title: Project Clinic
Duration: 1.0hrs

Day 3

Section 7: Deep Learning for Computer Vision 
Frameworks: TensorFlow, Keras
Abstract: Various types of Computer vision tasks
-    Understanding more advance image networks
-    Generative modelling for images
-    Examples of Style Transfer and Deep Dream

Section 8: Building a Model for Structured Data with TensorFlow 
Frameworks: TensorFlow, Datasets API, tf.data API
Abstract: Understanding the TensorFlow ecosystem APIs 
-    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

Section 9: Learning to use Object Detection and BERT with TensorFlow 
Frameworks: TensorFlow, Datasets API, tf.data API
Abstract: Understanding the TensorFlow ecosystem APIs 
-    What Object Detection is and how to use it
-    Building on Text Classification by using a pre-trained BERT model.

Title: Online Learning
Topics Covered:
-    Python Basics
-    Colabs and Notebooks
-    Neural Network Basics
-    Keras Basics
-    Convolutional Neural Networks (CNNs)
-    Recurrent Neural Networks (RNNs)
-    Preprocessing Patterns
-    Project Walk Throughs
-    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 80% 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

S$1,605 / pax (after GST)

Funding Support

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

Link to CITREP+ Programme Support table guide.

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

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

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 [email protected]

Dr Martin Andrews

Martin has over 20 years’ experience in Machine Learning and has used it to solve problems in financial modelling and the creation of Artificial intelligence (AI) automation for companies. His current area of focus and specialisation 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 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 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.

Topics: AI / Machine Learning / Deep Learning