San Francisco, CA

Avi Singh

Elite
@avisingh599

Research Scientist at Google DeepMind

mono-vo. An OpenCV based implementation of Monocular Visual Odometry

822

visual-qa. [Reimplementation Antol et al 2015] Keras-based LSTM/CNN models for Visual Question Answering

479

reward-learning-rl. [RSS 2019] End-to-End Robotic Reinforcement Learning without Reward Engineering

374

imitation-dagger. [Reimplementation Ross et al 2011] An implementation of DAGGER using ConvNets for driving from pixels.

90

vo-howard08. [Reimplementation Howard 2008] A MATLAB implementation of Visual Odometry using Andrew Howard's 2008 paper.

59

cog. [CoRL 2020] COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning

35

roboverse. A set of environments utilizing pybullet for simulation of robotic manipulation tasks.

29

awesome-rnn. Recurrent Neural Network - A curated list of resources dedicated to RNN

10

arduino-cashless-campus. An Arduino-based POS device with biometric (fingerprint) authentication.

5

verilog-hilbert-transform. A verilog implementation of 32-point Discrete Hilbert Transform

5

python-visual-odometry. Under construction now. When finished, it will do Stereo Visual Odometry using OpenCV and Python.

5

avisingh599.github.io. Webpage and blog: http://avisingh599.github.io

4

NeuralModels. A library for neural networks. Built using Theano.

3

gym_torcs. C++

2

icnn. Input Convex Neural Networks

2

svm-experiments. Scripts to tune hyperparameters when using libsvm and liblinear for linear, rbf and polynomial kernels.

2

multiworld. Python

2

homepage. The source code for my homepage. Based on Pixyll, powered by Jekyll.

2

mujoco-py. MuJoCo Python bindings

1

VQA_LSTM_CNN. Train a deeper LSTM and normalized CNN Visual Question Answering model. This current code can get 58.16 on OpenEnded and 63.09 on Multiple-Choice on test-standard.

1

ladder-1. Ladder network is a deep learning algorithm that combines supervised and unsupervised learning.

1

gps. Guided Policy Search

1

tensorflow. Computation using data flow graphs for scalable machine learning

1

pixyll. A simple, beautiful Jekyll theme that's mobile first.

1

HieCoAttenVQA. Jupyter Notebook

1

vae-tf. repository for the Variational Autoencoder (VAE) blogpost series from Fast Forward Labs

1

vime. Python

1
27
Apply