Name: Subhojeet Pramanik
Type: User
Company: University of Alberta
Bio: Reinforcement Learning Research at RLAI, Alberta Machine Intelligence Institute (Amii)
Twitter: subho_in
Location: Edmonton, Canada
Blog: www.subho.in
Subhojeet Pramanik's Projects
Differentiable Neural Computers, Sparse Access Memory and Sparse Differentiable Neural Computers, for Pytorch
PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM
A3C LSTM Atari with Pytorch plus A3G design
Sequence to Sequence and attention from scratch using Tensorflow
A single jupyter notebook multi gpu VAE-GAN example with latent space algebra and receptive field visualizations.
Just a test
Sequence to sequence learning using TensorFlow.
Source code of the model used in Tensorflow Speech Recognition Challenge (https://www.kaggle.com/c/tensorflow-speech-recognition-challenge). The solution ranked in top 5% in private leaderboard.
This notebook will try various unsupervised approaches to audio clustering to identify whether it can find a suitable cluster.