Deep-Learning Model Exploration and Development for NLP

[CVPR 2020] When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks

DeepSpamReview: Detection of Fake Reviews on Online Review Platforms using Deep Learning Architectures. Summer Internship project at CoreView Systems.

Adaptive and Focusing Neural Layers for Multi-Speaker Separation Problem

Graph SuperResolution Network using geometric deep learning.

A general framework for cascade correlation architectures in Python with wrappers to keras, tensorflow and sklearn

Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Deep Learning architectures in Tensorflow Keras, and PyTorch.

Deep learning architectures for in-air hand gesture recognition

Exploring RL ideas for deep neural network hyper-parameter search

Implementing and training/testing popular model architectures on the CIFAR10 dataset.

Deep Learning papers reading roadmap for anyone who is eager to learn this amazing tech!

Deep Learning architectures implemented in PyTorch Lightning

Code release for "Relaxed Weight Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series" (Oh, Wang, Tang, Sjoding, Wiens), MLHC 2019. https://arxiv.org/abs/1906.02898

Code release for "Learning to Exploit Invariances in Clinical Time-Series Data Using Sequence Transformer Networks" (Oh, Wang, Wiens), MLHC 2018. https://arxiv.org/abs/1808.06725

Notes on ML and DL with jupyter notebooks (python)

Tokenization is a way of separating a piece of text into smaller units called tokens. Here, tokens can be either words, characters, or subwords. Hence, tokenization can be broadly classified into 3 types – word, character, and subword (n-gram characters) tokenization.

My experimentations with Keras