Code Monkey home page Code Monkey logo

Hi there 👋

I am currently as a research engineer at Corpy.

My research interests lie at the intersection of machine learning and computational neuroscience. My focus is two-fold:

  1. Developing new methods for analyzing and interpreting neural datasets.
  2. Drawing inspiration from biological brains to design novel architectures and methods

More broadly, I am interested in using machine learning as a tool to elucidate the mechanisms that drive biological and artificial intelligence. For this, I believe modern paradigms such as self-supervised learning, multi-modal learning, and continual learning could offer invaluable insight into the mechanisms of learning.

Apart from my research, I am a core maintainer for Torchmetrics and a core contributor for PyTorch Lightning Bolts.

I previously worked at the Computational Vascular Biomechanics Lab as a PhD pre-candadiate in Biomedical Engineering at the University of Michigan, Ann Arbor. Before that, I completed my MS in Mechanical Engineering at the University of Minnesota, Twin Cities where I researched the computational phenotyping of thoracic aortic aneurysms in the Barocas Lab. I received my BS in Mechanical and Biomedical Engineering from Worcester Polytechnic Institute.

Shion Matsumoto's Projects

albumentations icon albumentations

Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

avalanche icon avalanche

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

cardiovascular icon cardiovascular

The cardiovascular repository contains C++ and Python programs useful for cardiovascular applications, in particular applications related to the SimVascular modeling and simulation software.

continual-learning-baselines icon continual-learning-baselines

Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.

deepsdf icon deepsdf

Learning Continuous Signed Distance Functions for Shape Representation

hyde icon hyde

A brazen two-column theme for Jekyll.

lightly icon lightly

A python library for self-supervised learning on images.

lightning icon lightning

Deep learning framework to train, deploy, and ship AI products Lightning fast.

lightning-flash icon lightning-flash

Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains

lsp-zero.nvim icon lsp-zero.nvim

A starting point to setup some lsp related features in neovim.

meme icon meme

PyTorch Lightning implementation of Mutually Supervised Multimodal VAEs (MEME)

metisfl icon metisfl

MetisFL is a federated learning framework that allows developers to easily federate their machine learning workflows and train their models across distributed data silos without ever collecting the data in a centralized location. The core of the framework is written in C++ and focuses on scalability, speed and resiliency.

metrics icon metrics

Machine learning metrics for distributed, scalable PyTorch applications.

numerical-linear-algebra icon numerical-linear-algebra

Jupyter notebooks on concepts from numerical/computational linear algebra. Inspired by Professor Rachel Thomas' class on computational linear algebra.

playground icon playground

PyTorch Lightning re-implementations of various neural network architectures

polars icon polars

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

pytorch_pcgrad icon pytorch_pcgrad

Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"

randnla.jl icon randnla.jl

Implementations of randomized numerical linear algebra algorithms in Julia

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.