Artificial neural networks are models of reasoning based on human brain functioning and have been successful in many real-world applications including pattern classification, regression, forecasting, etc. The course will introduce models, learning, implementations and applications of neural networks and deep learning.
To equip participants with the basic concepts and methodologies of neural networks and deep learning systems. In particular, this course covers the information processing techniques inspired by the workings of biological neural networks, which provides solution to interrogatives that current linear systems are not able to resolve. Basic neuron models, neural layers, feedforward networks, convolutional neural networks, autoencoders, and recurrent neural networks will be covered in the course. 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 model for solving real world applications and perform required simulations and implementations.
Fee with NEW SkillsFuture Series subsidy: S$337.05(inclusive of GST). *conditions apply
To be eligible for SF Series subsidy, participants:
- must be Singaporeans or Permanent Residents of Singapore
*Participants who do not fulfill the above criteria are not eligible for SF Series funding, and are required to pay the course fee in full.
Participants would be required to bring your own laptop with Python and Tensorflow Installed.
Technicians, engineers, data modelers, and computational scientists who are interested in developing neural network models to solve computational problems, including pattern/object recognition, regression, prediction, forecasting, etc. Knowledge of linear algebra, calculus, basic programming skills, and Python would be useful.
• Introduction to neural networks
• Pattern recognition
• Implementing neural networks, using Python and Theano
• Neural layers
• Feedforward neural networks
• Model selection and overfitting
• Convolutional neural networks
• Recurrent neural networks
• Gated RNN
|Cancellation & Refund Policy|
|A written notification to firstname.lastname@example.org or fax to
6774 2911 before course closing date.
|No cancellation charges (Full refund)|
|A written notification on or after course closing date.||No Refund
SkillsFuture Credit (if applicable):
- Participant to cancel their claim with WDA
- PaCE Collegereserves the rights to collect the full fee amount from the participant
|Given a 3 days notice before course commencement, companies may replace participants who have signed up for the course. Terms and conditions apply.
There is no replacement for participant utilising SkillsFuture Credit. Participant to cancel their SkillsFuture Credit claim with WDA.
|Terms and Conditions|
|• Course is subject to a minimum participation before commencement
• Course is subject to a first-come-first-serve basis in light of overwhelming responses
• PaCE Collegereserves the right to change or cancel any course or trainer, in light of unforeseen circumstances
• All details are correct at time of dissemination
|At PaCE College, participants’ personal information is collected, used and disclosed for the following purposes:
Jagath Rajapakse is Professor of Computer Engineering at the School of Computer Science and Engineering at the Nanyang Technological University (NTU), Singapore. He obtained Ph.D. degrees in electrical and computer engineering from the University of Buffalo. He was Visiting Professor of Biological Engineering at the Massachusetts Institute of Technology, Visiting Scientist at the Max-Plank Institute of Cognitive and Brain Sciences (Leipzig), and Visiting Fellow at the National Institute of Health (USA).
His current research interests are in brain imaging, and computational and systems biology. Professor Rajapakse has published over 300 research papers in scientific journals and conferences. He served as Associate Editor for the IEEE Transactions on Neural Networks and Learning Systems, the IEEE Transactions on Computational Biology and Bioinformatics, and the IEEE Transactions on Medical Imaging. He is a Fellow of Institute of Electrical and Electronics Engineering (IEEE).