anirbanl Goto Github PK

anirbanl.github.io

Personal Webpage of Anirban Laha

awesome-rl

Reinforcement learning resources curated

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

contrast

Jekyll Theme

corr-seq-labeling

Code for paper "Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks"

deep-learning-v2-pytorch

Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101

deep-reinforcement-learning

Repo for the Deep Reinforcement Learning Nanodegree program

discofuse

diverstiybasedattentionmechanism

files2rouge

Calculating ROUGE score between two files (line-by-line)

ganground

Functions and helpers related to GAN training in PyTorch

gcomm

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

jax-code

Code for the DL library JAX

jekyllblog

My blogs created through Jekyll

key-value-memory-networks

The implementation of key value memory networks in tensorflow

lola

Code release for Learning with Opponent-Learning Awareness and variations.

models

Models built with TensorFlow

pointer-generator

Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"

reason-scan

ReaSCAN is a synthetic navigation task that requires models to reason about surroundings over syntactically difficult languages.

rl-code

RL practice code

sampleproject

A sample project that exists for PyPUG's "Tutorial on Packaging and Distributing Projects"

scann

Google Research

sparse-structured-attention

Sparse and structured neural attention mechanisms

sparsegen

Code for the NeurIPS 2018 paper "On Controllable Sparse Alternatives to Softmax"

structureddata_to_descriptions

transformer_generalization

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

word2vec

Automatically exported from code.google.com/p/word2vec