sharansahu
Incoming PhD Stats & Data Science @ Cornell University | Prev. Computer Science @ UC Berkeley
Berkeley, CA
Pinned Repositories
Analyzing-The-Relationship-of-Spatial-Distribution-of-GHG-Emissions-and-Minority-Groups
ESPM 50AC Final Creative Project: Analyzing The Spatial Distribution of GHG Emissions and Minority Groups
calhacks-ml-model
Code for a differentially private Wasserstein GAN to create synthetic image and tabular data.
Citadel-Datathon-2021
Top 5 Project From Citadel Datathon 2021
CS-182-Project
WGAN Homework and Programming Assignment Creation For CS 182 Project
CS-267-Final-Project
Direct-Image-Matching
Utilized OpenCV, ORBDescriptors, FLANN, Homography/Affine Transformations, and a multi-layer convolutional architecture to do direct image matching via feature and key-point matching for scale-variant images
MLAutoFlow
MLAutoFlow is a package that allows users to push their custom-trained machine-learning models to Replicate without any installations or hassles. This tool is particularly useful for data scientists and developers who want to get their open-source machine learning models deployed fast without any hassles.
pdf-to-clustering
personal_portfolio
A personal portfolio website created using HTML, CSS, JS, and AOS to store personal projects and papers to show to friends, family, and future employers.
PrivSynth
PrivSynth is a Streamlit application designed to create differentially private tabular data using Differentially Private Wasserstein Generative Adversarial Networks (DPWGAN). This tool is particularly useful for users who need to generate synthetic data sets that closely resemble original data while ensuring the privacy of individual data entries.
sharansahu's Repositories
sharansahu/Direct-Image-Matching
Utilized OpenCV, ORBDescriptors, FLANN, Homography/Affine Transformations, and a multi-layer convolutional architecture to do direct image matching via feature and key-point matching for scale-variant images
sharansahu/PrivSynth
PrivSynth is a Streamlit application designed to create differentially private tabular data using Differentially Private Wasserstein Generative Adversarial Networks (DPWGAN). This tool is particularly useful for users who need to generate synthetic data sets that closely resemble original data while ensuring the privacy of individual data entries.
sharansahu/Analyzing-The-Relationship-of-Spatial-Distribution-of-GHG-Emissions-and-Minority-Groups
ESPM 50AC Final Creative Project: Analyzing The Spatial Distribution of GHG Emissions and Minority Groups
sharansahu/calhacks-ml-model
Code for a differentially private Wasserstein GAN to create synthetic image and tabular data.
sharansahu/Citadel-Datathon-2021
Top 5 Project From Citadel Datathon 2021
sharansahu/CS-182-Project
WGAN Homework and Programming Assignment Creation For CS 182 Project
sharansahu/CS-267-Final-Project
sharansahu/MLAutoFlow
MLAutoFlow is a package that allows users to push their custom-trained machine-learning models to Replicate without any installations or hassles. This tool is particularly useful for data scientists and developers who want to get their open-source machine learning models deployed fast without any hassles.
sharansahu/pdf-to-clustering
sharansahu/personal_portfolio
A personal portfolio website created using HTML, CSS, JS, and AOS to store personal projects and papers to show to friends, family, and future employers.
sharansahu/precision-recall-distributions
Assessing Generative Models via Precision and Recall (official repository)
sharansahu/sharansahu
Config files for my GitHub profile.
sharansahu/sharansahu.github.io
A personal portfolio website created using HTML, CSS, JS, and AOS to store personal projects and papers to show to friends, family, and future employers.
sharansahu/STAT-210B-High-Dimensional-PCA-Notes
sharansahu/stat453-deep-learning-ss21
STAT 453: Intro to Deep Learning @ UW-Madison (Spring 2021)
sharansahu/Surface-Deformity-Detection-With-CNNs
Machine learning methods and image processing were utilized to determine whether a surface contains a deformity. Through the development of a C++ program to generate surface deformities given image length, width, maximum deformity radius, and sample size as the training set, we utilize machine learning classifiers, namely Convolution Neural Networks (CNN), Support Vector Machines (SVC), and K-Means Clustering (KMC) to classify surfaces with either no impact, low impact, medium impact, or high impact.
sharansahu/research_website
My research website : )
sharansahu/STAT-241B-Final-Project
sharansahu/visualize-rag
This project provides a tool for loading, embedding, and querying PDF documents using OpenAI or Ollama models. It enables the creation of a vector database to store document embeddings, facilitates interactive question-answer sessions, and visualizes the results using Spotlight. Perfect for extracting information from large sets of documents