harsha070 Goto Github PK
Name: Sree Harsha Tanneru
Type: User
Bio: Research interests - Uncertainty quantification, Information theoretic machine learning, post-hoc explainability
Name: Sree Harsha Tanneru
Type: User
Bio: Research interests - Uncertainty quantification, Information theoretic machine learning, post-hoc explainability
Comparing Information Bottleneck compression and Regularized Variational Autoencoders
Resource-adaptive cluster scheduler for deep learning training.
Algorithms
Fall 2023 Capstone Project 11
In-training approaches for fairness in graph neural networks
Simple Distributed Deep Learning on TensorFlow
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
ML Systems Research Project
CS283: Advanced Computer Vision Course Project
Data Pipeline
FaceNet: A Unified Embedding for Face Recognition and Clustering
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
Minimal Jekyll blog styled to resemble the look and layout of Edward Tufte's books
Hyper-Parallel Approximate Nearest Neighbor Search
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Learn Java
Making LLM training as close to metal as possible
Used SVMs, Decision Tress (Random forests, Boosting techniques) to predict ore concentrate in flotation process
Large Language Models and Diffusion for Zero-Shot Reinforcement Learning
Networks Notes
Numerical simulation of lid driven cavity using SIMPLE algorithm
Super resolution reconstruction in computational fluid dynamics. Proposed a novel autoencoder architecture to improve over existing results.
Machine Translation
We introduce a new loss term as an attempt to improve sharpness in variational autoencoders. Attempted the same on Variational Autoencoder generative adversarial network.
stream lit cloud demo script
This is the repository for the distill web framework
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.