Currently I am leading artificial intelligence with my colleagues in ensemblecap.ai, an AI hedge fund based in Singapore comprising quants and traders from JPMorgan and Nomura. I have built the whole AI tech stack in a production environment with rigorous time-sensitive and fail-safe software testing powering multi-million dollar trades daily. Additionally, I co-run, as portfolio manager, our systematic end-to-end deep learning portfolio with the Chief Investment Officer.

I am also an NVIDIA Deep Learning Institute instructor leading all deep learning workshops in NUS, Singapore and conducting workshops across Southeast Asia.

My passion for enabling anyone to leverage on deep learning has led to the creation of Deep Learning Wizard where I have taught and still continue to teach more than 2000 students in over 60 countries around the world. The course is recognized by Soumith Chintala, Facebook AI Research, and Alfredo Canziani, Post-Doctoral Associate under Yann Lecun, as the first comprehensive PyTorch Video Tutorial.

I have taught Deep Learning Foundations with Alfredo Canziani at Rwanda, Africa for the African Masters in Machine Intelligence (AMMI) in 2018 supported by Google and Facebook.

In my free time, I’m into deep learning research on hyperspectral satellite imaging and financial time series with researchers in NUS, Montreal Institute for Learning Algorithms (MILA), New York University (NYU), African Institute for Mathematical Sciences (AIMS) and Hong Kong University of Science and Technology (HKUST). I am a research scholar in NExT (NUS).

I was previously conducting research in meta-learning for hyperparameter optimization for deep learning algorithms in NExT Search Centre that is jointly setup between National University of Singapore (NUS), Tsinghua University and University of Southampton led by co-directors Prof Tat-Seng Chua (KITHCT Chair Professor at the School of Computing), Prof Sun Maosong (Dean of Department of Computer Science and Technology, Tsinghua University), and Prof Dame Wendy Hall (Director of the Web Science Institute, University of Southampton).

I graduated from NUS where I was an NUS Global Merit Scholar, Chua Thian Poh Community Leadership Programme Fellow, Philip Yeo Innovation Fellow, and NUS Enterprise I&E Praticum Award recipient.

Deep Learning Courses

These are some of the courses I created that will gradually build up your deep learning capabilities. We are an NVIDIA Inception Partner.
Main Website, Deep Learning Wizard
Practical Deep Learning with PyTorch, Deep Learning Wizard

Upcoming Talks/Workshops

Natural Language Processing with Deep Learning, NVIDIA, Singapore, 2019
Computer Vision with Deep Learning 2.0, NVIDIA, Singapore, 2019

Key Papers

Neural Optimizers with Hypergradients for Tuning Parameter-Wise Learning Rates, ICML 2017

Past Talks/Workshops

Foundations of Deep Learning, African Masters of Machine Intelligence (AMMI), Google & Facebook, Kigali, Rwanda, November 2018

AI and Unstructured Analytics in Fintech, Nanjing, China, November 2018 Post Link

PyTorch Developer Conference, Facebook, San Francisco, USA, October 2018

Hyperparameter Optimization with Neural Optimizers, Big Data & AI Leaders Summit, Singapore, September 2018

Image Classification Workshop, NUS-NUH-MIT Datathon, NVIDIA, Singapore, July 2018

Object Detection with DIGITS, NVIDIA, Singapore, June 2018

Image Classification with DIGITS, NVIDIA, Singapore, May 2018

Meta Learning, AutoML, ICML, Sydney, 2017

Deep Learning for Self-Driving Cars and Medical Diagnostics, NVIDIA, Singapore, 2017

Scalable Hyperparameter Optimization, REWORK Deep Learning Summit, Singapore, 2017

Past Projects

Residual Networks with TensorFlow

Wide Residual Networks with TensorFlow

Large Scale Identification of Multiple Digits from Real-world Images with Convolutional Neural Networks (CNN)

Training a Smart Cab (Reinforcement Learning)

Identifying Customer Segments (Unsupervised Learning)

Building a Student Intervention System (Supervised Learning)

Predicting Boston House Prices

The Incredible PyTorch
This is an awesome curated list of tutorials, papers, projects, communities and more relating to PyTorch.

A Deep Learning Amazon Web Service (AWS) AMI that is open, free and works. Run any deep learning framework in less than 5 minutes including TensorFlow, Keras, PyTorch, Theano, MXNet, CNTK, Torch, and Caffe.

Past Articles

The Great Conundrum of Hyperparameter Optimization, REWORK, 2017


Global Merit Scholarship 2014-2018, NUS
NUS top scholarship with only 4 awarded in NUS across all faculties for the year of my admission.
Full scholarship amounting to more than $100,000 covering tuition, allowance, accommodation, and overseas trips.

Dean’s List 2015/2016, NUS
Top 5% of my cohort.

I&E Practicum Award 2017, NUS
$10,000 Award.

Philip Yeo Innovation Fellowship 2017, NUS
$20,000 Award with mentorship by Philip Yeo, Chairman of Spring Singapore.
I am fortunately also under the mentorship of Kiren Kumar (AMD, EDB) and Abel Ang (CEO, EDIS).

Valedictorian (Reserve) Class of 2018, NUS
It happened.

Chua Thian Poh Community Leadership Programme Fellow 2018, NUS
Established with generous gifts from Mr Chua Thian Poh, the Centre aims to nurture Singapore’s next generation of community leaders. These leaders will not only be intellectually engaged with social and community issues, but will also be passionate about addressing social and community challenges in Singapore.

Online Profiles


Languages, Libraries and Frameworks

Machine Learning Database General Programming
PyTorch Apache Cassandra C++
TensorFlow Apache Spark Python
Keras   Bash Scripting
TensorLayer   LaTeX


I would like to thank all my readers for their encouraging participation on this Github page. I would also like to thank Github Pages for serving this respository of notes for free.

I would like to give full credit to the respective authors for their free courses and materials online like Andrew Ng, Data School and Udemy where my notes are from them. These personal notes are meant for my personal review but I have open-sourced my repository of personal notes as a lot of people found it useful.

Take note that I’m currently concentrating entirely on building materials for Deep Learning with PyTorch from mastering deep learning, to deploying deep learning algorithms in production, and to to solve many problems through Deep Learning Wizard.

Tags: about