eashanadhikarla

MemoryDef

Memory Defense: More Robust Classification via a Memory-Masking Autoencoder, https://arxiv.org/pdf/2202.02595.pdf

wfm

Face Mask Detection on Real-World Webcam Images; https://doi.org/10.1145/3462203.3475903

image-manipulation-detection

I developed the state-of-the-art YOLOv5x6-TTA for image manipulation detection

Facial-Recognition-with-DNN

Working with the accuracies and flaw removal strategies with re-implementation of OpenFace/Google’s Face-Net, for improving the range of applications in the domain of Security. Resolved the false positive 2-D inputs by introducing more features in Stage 1 (face detection) as a.) Orientation Normalization b.) 3D surface representation.

Astroturfing-Review-System

This is a filtering model with machine learning algorithm to filter-out the fake reviews and hence the fake reviewers from committing review frauds. I used amazon reviews data sets to built a stochastic model on top of it.

data-centric-ai

Resources for Data Centric AI

seqGAN

Seq-GAN is a unique approach which models the data generator as a stochastic policy in reinforcement learning to solve the problem. The Reinforcement Learning reward signal comes from the GAN discriminator judged on a complete sequence, and is passed back to the intermediate state-action steps using Monte Carlo search.

Atomic-Commit-Protocol-2PC

This implementation is a multi-threaded Replicated Hash Table with a two phase commit - atomic commitment protocol (ACP).

Clockchain

The purpose of this assignment is to get you thinking about what it means for something to happen "before" something else. You will explore this notion through the journey of this project.

coding-interview-university

A complete computer science study plan to become a software engineer.

congestion-control-bbrv2

Exploring the use of the BBRv2 Congestion Control Algorithm for use on DataTransfer Nodes

diffusion

Denoising Diffusion Probabilistic Models

DL4Sci

Deep Learning School in Lawrence Berkeley National Lab

eashanadhikarla.github.io

finnts

Microsoft Finance Time Series Forecasting Framework (FinnTS) is a forecasting package that utilizes cutting-edge time series forecasting and parallelization on the cloud to produce accurate forecasts for financial data.

GPT4RoI

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

kibana-data-retrieval

Fetching high-level stats from the ELK stack for data transfer nodes

ml-fastvit

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization"

ml-mobileclip

This repository contains the official implementation of the research paper, "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" CVPR 2024

Physical-Intrusion-Detection-System

A prototype model which can sense intruders entering into the building with the help of infrared sensor and simultaneously notifying the owner about the intruder by sending notification via call and capturing a snapshot.

pytorch-adversarial_box

PyTorch library for adversarial attack and training

PyTorch_CIFAR10

Pretrained TorchVision models on CIFAR10 dataset (with weights)

Random-Erasing

Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST

RobustAdversarialNetwork

A pytorch re-implementation for paper "Towards Deep Learning Models Resistant to Adversarial Attacks"

Robustness-Aware-Pruning-ADMM

Code release for "Adversarial Robustness vs Model Compression, or Both?"

simsg

supreme-garbanzo

KR&R

tiny-faces-pytorch

Finding Tiny Faces in PyTorch

Twitter-Trend-Analyzer

Using twitter data to do analysis and extract the most frequently used dictionary for political campaign. This application has been been implemented in C++ and MongoDB back-end.

webcam-image-gathering

To capture images periodically through public webcams.