Name: Mohammad Mahdi Kamani
Type: User
Company: AMD
Bio: Senior Research Scientist at AMD. Working on Efficient Gen AI, Federated Learning, Distributed Optimization, Model Compression, and Edge AI.
Twitter: mmkamani7
Location: Bellevue, WA
Blog: https://mmkamani.com
Mohammad Mahdi Kamani's Projects
The source code for the paper titled: "Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation", accepted to BMVC2021
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
An open source library for deep learning end-to-end dialog systems and chatbots.
Python class to access Affectiva's Emotion as a Service API
Emotion recognition using DNN with tensorflow
Implementation of Fair PCA algorithm using Pareto Descent
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
A framework for implementing federated learning
Distributed and Federated approaches implemented for MLX
This is a generic repository for benchmarking different federated and distributed learning algorithms using PyTorch.
This repository implements different ways to speedup the calculation and estimation of Shapley Value using SHAP library.
A C++ standalone library for machine learning
Implementation of Local Updates Periodic Averaging (LUPA) SGD
OpenMMLab Image Classification Toolbox and Benchmark
Personal website of MM. Kamani
Config files for my GitHub profile.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Deep Learning (with PyTorch)
:star: Use repo badges (build passing, coverage, etc) in your readme/markdown file to signal code quality in a project.
ResNet for CIFAR with Estimator API and tf.keras.Model class
Implementation of Redundancy Infused SGD for faster distributed SGD.
In this repository you can see the code for skeletonization of binary images using our novel fuzzy inference system.
This repository implements skeleton matching algorithm.
In this repository, we implement Targeted Meta-Learning (or Targeted Data-driven Regularization) architecture for training machine learning models with biased data.
Proceedings of AISTATS 2021