I'm a recent junior college graduate and Machine Learning research student from Singapore. Since 2015, I've been dabbling with Deep Learning at a few startups. Catch my work on Computer Vision and Natural Language Processing.

Do check out my resume and coverpage!

Featured on

Publications

I'm an editor and writer for 7 journals and publications where I write articles and tutorials on Machine Learning and Data Science. Here are a few 'best-selling' articles:

Rishabh Anand in TensorFlow

Jul 22 . 7 min read

Training Your Models on Cloud TPUs in 4 Easy Steps on Google Colab

I trained an NMT model on a TPU and now feel like a superhero...

Read more...

Rishabh Anand in Towards Data Science

Mar 16 . 7 min read

Crash Course in Quantum Computing Using Very Colourful Diagrams

Almost everything you need to know about Quantum Computing explained...

Read more...

Rishabh Anand in Hackernoon

May 23 . 6 min read

CatGAN: cat face generation using GANs

Detailed review of GANs and how to waste your time with them...

Read more...

Rishabh Anand in The Startup

Nov 5 . 17 min read

Transition, Tenacity and Ten Thousand Dollars

From idea to execution, I tried to set a path for myself and learned some lessons along the way...

Read more...

See More

Projects

I spend my free time writing code and open-sourcing it online. I currently have 84 public open-source projects on GitHub. I love to work on Machine Learning problems specifically in the Natural Language space. Here are some trending repositories:

sight

👁Sightseer: State-of-the-art Computer Vision and Object Detection for TensorFlow

Python

gpt2client

✍🏻GPT2Client: Easy-to-use TensorFlow Wrapper for GPT-2 117M, 345M, 774M, and 1.5B Transformer Models

Python

CatGAN

Generative Adversarial Network (GAN) that generates cat faces using Google's Quick, Draw! dataset 🤖😺

Python

Network-Optimisation

Neural Network Hyper-parameter Tuning with Genetic Algorithms 🤖🧬

Python

See More

Events

I love attending conferences and talks. What's even cooler? I've got to speak at a few! I've found conferences and meetups to be the best ways to network with the community on the latest and greatest technologies. If interested in having me as a speaker, feel free to email me!

FOSSASIA Summit 2020

20 Mar 2020 . LLI, SINGAPORE

Gave a crash course to the TensorFlow ecosystem with some live-coding. My first e-conference talk!

PyCon Educators Summit SG

25 June . *SCAPE, SINGAPORE

Spoke to educators from various schools, universities, and institutions about adding AI courses into their curricula

FOSSASIA Summit 2019

15-16 Mar . LLI, SINGAPORE

Introduction to Machine Learning through the Linear Regression and Single Layer Perceptron models

TensorFlow Meetup

18 Dec . Google APAC HQ, SINGAPORE

Overview of the tools and APIs a friend and I built to simplify learning of ML concepts and TensorFlow/Keras syntax

BuildingBloCS Conference

9 Jun . NUS SoC, SINGAPORE

Introduced secondary students to ML and Data Science with the k-Nearest Neighbours algorithm in Python

Resources

What's better than writing code? Publishing it for the world to see, of course! Notebooks have always been my go-to resource for conference talks and workshops as I can get my ideas across without any fuss. Here are a few of my trending Colab notebooks:

COVID-19 X-ray Classification with CNNs

Here, I build a simple CNN and train on the COVID-19 X-ray dataset. I connect it to TensorBoard and log some custom metrics. I wrote this for my talk at FOSSASIA Summit 2020.

Neural Machine Translation in TensorFlow using TPUs

This tutorial covers NMT from English to German. The model is a seq2seq LSTM that's trained on a Cloud TPU. Let's observe how TPU training affects the model's performance.

Single Layer Perceptron in Basic TensorFlow

A short tutorial on data preprocessing and building models with TensorFlow. The notebook covers the basics of numpy and pandas and uses the Iris dataset as reference.

Linear Regression with Numpy

Barebones Linear Regression model built using numpy. Here, I go through the equations and Mean Squared Error loss function to train the model on randomly generated data.