Advanced Computer Vision with Deep Learning | SGInnovate

DATE: TBC

Location

TBC

Advanced Computer Vision with Deep Learning

Organised by SGInnovate and Red Dragon AI

Together with Red Dragon AI, SGInnovate is pleased to present the second module of the Deep Learning Developer Series. In this module, we go beyond the basic skills taught in module one such as Convolutional Neural Networks (CNNs). This would expand your ability to build modern image networks using a variety of architectures and for applications beyond simple classification.

About the Deep Learning Developer Series:

The 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 for modular customisation according to your own pace and preference. In every module, you will have the opportunity to build your own Deep Learning models as part of your main project. You will also be challenged to use your new skills in an application that relates to your field of work or interest.

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
     

About this module:

Building on the lessons from the first module, we will be going beyond TensorFlow and Keras. PyTorch and TorchVision, which are often used for research in Computer Vision, will be introduced.

To understand the current state-of-the-art technologies, we will review the history of ImageNet winning models and focus on Inception and Residual models. We will also look at some of the newer models such as NASNet and AmoebaNet, and explore how the field has gone beyond hand-engineered models.

One key skill that you will acquire is how to use these modern architectures as feature extractors and apply them to create applications like image search and similarity comparisons. You will also discover how to do such tasks such as object detection and learn how models (like YOLO) are able to detect multiple objects in an image.

You will also learn about image segmentation and classification at the pixel level. This will involve using architectures like U-Nets and DenseNets. Furthermore, you will learn how they are used in a variety of image segmentation tasks from perception for self-driving cars to medical image analysis.

As with the other Deep Learning Developer modules, you will have the opportunity to build multiple models yourself.

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

In this course, participants will learn: 

  • Advanced classification and objection detection
  • An introduction into PyTorch and TorchVision
  • Skills to create applications like image search and similarity comparisons
  • About image segmentation and classification at the pixel level with architectures like U-Nets and DenseNets, and how they are used in a variety of image segmentation tasks

Recommended Prerequisites:

 


Day 1

08:45am – 09:00am: Registration
09:00am – 10:30am: Convolutional Neural Networks (CNNs) Recap Part 1
Frameworks: TensorFlow, Keras

  • Convolution math in layers
  • Pooling and Strides
  • AlexNets
  • Building CNNs
  • Calculating the parameters and shapes of various networks
  • Tuning CNNs
  • Visual Geometry Group (VGG) network 

10:30am – 10:45am: Tea Break
10:45am – 12:30pm: CNNs Recap Part 2
Frameworks: TensorFlow, Keras 

12:30pm – 1:30pm: Lunch
1:30pm – 3:30pm: Intermediate CNNs Part 1
Frameworks: TensorFlow, Keras, PyTorch

  • Modern Convolutional Nets
  • Transfer learning with CNNs and fine tuning
  • Inception architectures
  • Residual networks
  • ImageNet history and applications
  • Building a classifier using transfer learning
  • Kaggle competition for images part 1
  • Start personal project 1

3:30pm – 3:45pm: Tea Break
3:45pm – 5:30pm: Intermediate CNNs Part 2
Frameworks: TensorFlow, Keras, PyTorch

6:30pm – 6:00pm: Closing comments and questions

Day 2

08:45am – 09:00am: Registration
09:00am – 10:30am: CNN Architecture Part 1
Frameworks: TensorFlow, Keras, PyTorch

  • Auto Encoders
  • Repurposing CNN models
  • Object detection 
  • YOLO
  • Build an image search system
  • Continue personal project 1

10:30am – 10:45am: Tea Break
10:45am – 12:45pm: CNN Architecture Part 2
Frameworks: TensorFlow, Keras, PyTorch 

12:45pm – 1:45pm: Lunch
1:45pm – 3:45pm: CNNs Segmentation Part 1
Frameworks: TensorFlow, Keras, PyTorch 

  • Image search
  • Segmentation networks
  • U-Net and skip connections architectures
  • Batch normalisation

3:45pm – 4:00pm: Tea Break
4:00pm – 5:30pm: Facial Recognition 
Frameworks: TensorFlow

5:30pm – 6:00pm: Closing comments and questions

Participants will be given two weeks to complete their online learning and individual project. 

Online Learning 

  • Building CNNs from scratch
  • Building auto encoders
  • Understanding object detection and location models
  • Style transfer
  • Fast style transfer

Assessments

Participants must fulfil the criteria stated below to pass the course.

1. Online Tests: Participants are required to score a minimum grade of more than 75% 

2. Project: Participants are required to present, and achieve a pass on 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).


*Please see ‘Guide for CITREP+ funding eligibility and self-application process’  below for more information. 

Funding Amount: 

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

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

  • CITREP+ covers up to 100% 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 Criteria:

  • Singaporean / PR
  • Meets course admission criteria
  • Sponsoring organisations 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 “Individuals / Self-Sponsored” category
  • Sponsoring SMEs who wish to apply for up to 90% funding support for course must meet the 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:

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

In partnership with:Driven by:

  

In partnership with employers to support employability:

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

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: Artificial Intelligence / Deep Learning / Machine Learning / Robotics