Name: Vivek Talwar
Type: User
Company: International Institute of Information Technology, Hyderabad.
Bio: Research Interests : Multimodal Learning, Federated Learning, Continual Learning,
Mechanistic Interpretability.
distributed systems+ML+hpc acceleration
Twitter: gpubrr042
Location: Hyderabad, India
Vivek Talwar's Projects
Easy-to-use AdaHessian optimizer (PyTorch)
Reinforcement_Learning_in_online_Advertisemnt_Industry
Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
http://nlp.seas.harvard.edu/2018/04/03/attention.html
Applied Deep Learning
Avalanche: an End-to-End Library for Continual Learning.
Diffusion Models in Medical Imaging
JAX - A curated list of resources https://github.com/google/jax
Reading list for research topics in multimodal machine learning
A curated list of awesome Python frameworks, libraries, software and resources
Official codebase used to develop Vision Transformer, MLP-Mixer, LiT and more.
A flexible framework of neural networks for deep learning
Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
CodeGen is an open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
Pytorch implementation of COIN, a framework for compression with implicit neural representations 🌸
Continual Learning tutorials and demo running on Google Colaboratory.
The long missing library for python confidence intervals
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
Let us control diffusion models
A simple HTML web form for User Authentication and Registration
Collaboration space for SAS and others to understand, model, and mitigate COVID-19 through analytics
COVID deterioration prediction based on chest X-ray radiographs via MoCo-trained image representations
A 16-bit MIPS CPU built in HDL Verilog
Custom implementation of Support Vector Machines using Python and NumPy
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 175 universities.
daiict hackathon
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...