Skip Ribbon Commands
Skip to main content

Course Detail

Top AI Skills to Learn - Deep Learning


Artificial neural networks are computational models of prediction and reasoning based on biological neural network in the brain. Deep neural networks  and learning have recently achieved human like performances in visual recognition tasks and been successful in many real-world applications.

The course will introduce models of neural network, deep learning algorithms, and their implementations in software.  This course will take participants from simple neuron models to applications of deep neural networks learning.


Date(s): 13 to 13 January 2020
Time: 9:00AM to 5:00PM
Venue: NTU@one-north campus, Executive Centre (Buona Vista)
Closing Date:
30 December 2019
Course Fee: Standard: S$642.00   View more
Registration fees inclusive of:
  • Prevailing GST
  • Course materials
  • Light refreshments
  • Complimentary lunch


To equip participants with the basic concepts and methodologies of neural networks and deep learning systems. The course covers basic neuron models, neural layers, deep feedforward networks, convolutional neural networks, and recurrent neural networks. Students will be given hands-on experience in building neural network models, using Python and Tensorflow libraries.

After taking this course, from shallow to deep neural networks, students will be able to design and select suitable neural network models for solving real world applications and perform required simulations and implementations on computing machines effectively.


1. Neural networks basics

2. Pattern recognition and Regression

3. Implementing neural networks, using Python and Tensorflow

4. Neural layers

5. Deep feedforward neural networks

6. Convolutional neural networks (CNN)

7. Recurrent neural networks (RNN)

Read more


Rajapakse, Jagath C

Dr. Jagath Rajapakse is Professor of Computer Engineering at Nanyang Technological University. He has over 20 years of experience in teaching Neural Networks and Deep Learning and performed research in related areas.

  • Data/Business/Financial Analyst
  • Data Analytic/Data Science Professional
  • Hardware/Data/Systems/IoT Engineers
  • Researchers
Standard Course Fee S$642.00
Course fee payable after SSG funding, if eligible under various schemes

Cat-A SSG Funded Courses1


Enhanced Training Support for SMEs (ETSS) 2


Mid-Career Enhanced Subsidy (MCES)3


Workfare Training Support (WTS)4

Standard Course Fee $642.00
Course fee payable after funding or subsidy, if eligible under various schemes
Course fee payable after Discount^

Group of 3 pax and above


NTU/NIE Alumni, Staff & Students


NTUC Member

- All fees stated are inclusive of 7% GST
- SkillsFuture Credit can be used to offset course fees payable.
With effect from 1 April 2020, eligible Singaporeans can start using their one-off SkillsFuture Credit top-up (up to S$500 credit), claimable for full range of SkillsFuture Credit-eligible courses offered by PaCE@NTU. For more information, please visit
1 Cat-A SSG Funded Courses - Eligible Singapore Citizens and PRs may enjoy up to 70% of the course fee. For more information, visit
Enhanced Training Support for SMEs (ETSS) - SME-sponsored employees (Singapore Citizens and PRs) may enjoy subsidies up to 90% of the course fee.
For more information, visit
3 Mid-Career Enhanced Subsidy (MCES) - Singaporeans aged 40 and above may enjoy subsidies up to 90% of the course fee.
For more information, visit

4 Workfare Training Support (WTS) - Singaporeans aged 35 and above (13 years and above for persons with disabilities) and earn not more than S$2,000 per month, may enjoy subsidies up to 95% of the course fee. For more information, visit
- The NTUC Training Fund (SEPs) is applicable for courses under the SkillsFuture Series courses. For more information, visit

^ Discount cannot be used in conjunction with other SSG funding scheme or NTU Alumni Course Credit. Participants are eligible for only ONE of the discount schemes.
Not sure which programme to go for? Use our programme finder
Loading header/footer ...