Name: Akash Srivastava
Type: User
Company: MIT, IBM, University of Edinburgh, previously Microsoft Research and Microsoft
Bio: Chief Architect, LLM Alignment, IBM (MIT-IBM Watson AI Lab), Previously, PhD Student of @casutton at UoE, RIKEN AIP (Tokyo), Microsoft Research
Location: Cambridge, US | Edinburgh | Reading | Sheffield, UK
Blog: http://akashgit.github.io/
Akash Srivastava's Projects
Tensorflow implementation for prodLDA and NVLDA.
python version of bnp2
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
Autoencoding Variational Inference For Deep PAM
Code for training Generative Adversarial Networks (GANs) and evaluating the models' mode collapse
Getting Started Material
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
NN implementation
A brazen two-column theme for Jekyll.
Online variational Bayes for latent Dirichlet allocation (LDA)
The Jekyll Butler.
Over time I repeatedly use these lines of code but always forget that I already wrote them.
PyTorch implementation of AVITM
Python wrapper to small NORB dataset
TensorFlow implementation of Neural Variational Inference for Text Processing
VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
Quick start guide to setting up a GPU powered notebook in Watson Studio and train a GAN.