ripankundu Goto Github PK
Name: Ripan Kumar Kundu
Type: User
Company: University of Missouri-Columbia
Bio: Explainable Machine learning & Deep learning, Cyber security, Virtual reality, Cyber physical system
Location: Columbia, Missouri, USA
Name: Ripan Kumar Kundu
Type: User
Company: University of Missouri-Columbia
Bio: Explainable Machine learning & Deep learning, Cyber security, Virtual reality, Cyber physical system
Location: Columbia, Missouri, USA
500 AI Machine learning Deep learning Computer vision NLP Projects with code
Adversarial attacks - Time-Series data - LSTM - Regression - Classification
Tree-based local explanations of machine learning model predictions
Court of XAI - A Python library for the systematic comparison of feature additive explanation methods.
To track the orientation of the sensor using rotation vector to get the relative orientation of the sensors
Differentially Private Synthetic Data Generation [DP-SDG] - Experimental Setups & Knowledge Base - WORK IN PROGRESS
EquiBind: geometric deep learning for fast predictions of the 3D structure in which a small molecule binds to a protein
This research work focuses on comparing the existing approaches to explain the decisions of models trained using time-series data and proposing the best-fit method that generates explanations for a deep neural network. The proposed approach is used specifically for explaining LSTM networks for anomaly detection task in time-series data (satellite t
Gaze-enabled Augmented Reality
Resources for Machine Learning Explainability
Implementation of the InterpretTime framework
Repository for the DBSec 2023 paper "(Local) Differential Privacy has NO Disparate Impact on Fairness"
Implementation of local differential privacy mechanisms in Python language.
Code for paper: Are Large Language Models Post Hoc Explainers?
This paper summarizes a deep learning-based approach with an LSTM trained on the widely used Oxford battery degradation dataset and the help of generative adversarial networks (GANS).
1Lehrst ̈uhle des Instituts f ̈ur Elektrische EnergietechnikInstitut f ̈ur Elektrische EnergietechnikFakult ̈at f ̈ur Informatik und ElektrotechnikUniversit ̈at RostockMasterarbeit on the subject ofINVESTIGATING EVENTS AND ANOMALY DETECTION FORCYBER-PHYSICAL POWER SYSTEM USING ARTIFICIALINTELLIGENCE
This project include different Convolutional Neural Networks (CNN) architecture including (Resnet, Inception, NasNetLarge, VGG16 & 19)
Pytorch implementation of various neural network interpretability methods
A python package for processing eye movement data
Edge Detection by applying Stencil code on Image
Investigation different methods to fuse data from different sensor like Gyroscope, Accelerometer, Magnetometer for sensor fusion algorithm
Code samples and documentation for SmartNoise differential privacy tools
Repository for Euro S&P submission "SoK: Modeling Explainability in Security Monitoring for Trust, Privacy, and Interpretability"
Source code of the paper "On the Soundness of XAI in Prognostics and Health Management (PHM)".
[IEEE VR'22] SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers
Privacy-preserving generative deep neural networks support clinical data sharing
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.