Computer Vision with Deep Learning

From voice-activated assistants to facial recognition in photographs, many new applications of computer vision techniques have become part of our daily lives.

Developed for beginners, this is a four-day course that introduces participants to the field of computer vision, which involves the extraction, analysis and understanding of useful information from images. Then, the course will go on to cover machine learning and deep learning.

Participants will be taught to solve image recognition problems through Convolutional Neural Network and TensorFlow, as well as how to use tools to create deep learning models. Finally, they will put their training of data sets to the test by working with recognising real images. 

 

Learning Objectives

By the end of the course, participants will be able to:

  • better understand image processing fundamentals

    • image format and format conversion

    • image normalisation

    • convolution and pooling

  • understand the purpose of image processing for learning and recognition

  • set up TensorFlow for CPU, Keras and Jupyter Notebook

  • gain an introduction to Python Image Library (PIL)

  • carry out image displaying/plotting

  • gain an overview of Neural Networks and machine learning in

    • oneural units and tensors

    • cost functions

    • gradient descent

    • activation

  • understand what Nodes, Graph and Session are

  • train models with large data sets

  • create a model for character recognition

  • use TensorBoard Visualisations

  • understand Convolutional Neural Network (CNN) and its advantages in image recognition

  • configure CNN for image recognition

  • train and test the CNN model

  • acquire understanding on deep learning on the Cloud

  • gain knowledge about TensorFlow on Amazon Web Services (AWS)

  • understand what Google Cloud Vision Application Programming Interface (API) involves

Who should attend?

Anyone seeking to learn how to solve image recognition problems with deep learning or those who already have the basics of machine learning and deep learning and desire to upgrade their competencies. No prior knowledge of computer vision is required.

Entry Requirement

Applicants should possess at least a Diploma in ICT or engineering. Prior basic computer programming experience will be an advantage.

Certification

Participants will be awarded the Certificate of Attendance by Republic Polytechnic upon meeting 80% of the attendance requirement.

Course Date Course Venue
9 - 12 March 2021 This course will be conducted online

If you are not available for the dates above, we would like to hear from you by clicking here

Course Duration

4 Days

Full Course Fee (Others) Singapore Citizens aged 40 & above SME-employed Singapore Citizens & SPR Singapore Citizens aged below 40 OR Singapore PR
$738.30 $73.83 $83.49 $221.49


Note:
*Payment may be made using SkillsFuture Credit.
*Fees reflected are inclusive of GST (Goods & Service Tax).
*From 1 July 2020, Workfare Training Scheme (WTS) and fee subsidy under WTS will cease. WTS will be
replaced by Workfare Skills Support Scheme (WSS). For more information on WSS, please refer to www.wsg.gov.sg/programmes-and-initiatives/workfare-skills-support-scheme-individuals.html

Republic Polytechnic reserves the right to make changes to the course fee and application closing dates without prior notice. The commencement of each course is subject to sufficient number of participants.

All information is accurate at time of publishing.

Last updated on 20 Nov 2020

Need more help?

If you are still unsure about which course to pursue, please contact our Academy for Continuing Education.  

Fees quoted are inclusive of GST. Republic Polytechnic reserves the right to make changes to the course fees and application closing dates without prior notice. The commencement of each course is subject to a sufficient number of participants. All information is accurate at time of publishing.