Coder Social home page Coder Social logo

Hi there 👋

I research foundation models from the unique perspectives of visualization and dynamical systems.

Talk to me about

  • 🧠 Hopfield Networks
  • 🧩 Understandable latent spaces
  • 🦾 AI Frameworks/libraries
  • 🧱 Full stack development

I try to make all of my work+research public and open source.

I am affiliated with the Visual AI Lab at IBM Research & PoloClub at GA Tech.

I work closely with Hendrik Strobelt, Dmitry Krotov, Polo Chau.

Benjamin Hoover's Projects

.tmux icon .tmux

🇫🇷 Oh My Tmux! Pretty & versatile tmux configuration made with ❤️ (imho the best tmux configuration that just works)

associative-memory-demo icon associative-memory-demo

Hopfield Networks are a powerful framework to view why machine learning is so effective. What is it about them that works so well?

barebones-hamux icon barebones-hamux

Minimal library to construct Hierarchical Associative Memories (i.e., Super-powered Hopfield Networks). Research code designed to be easy to use.

exbert icon exbert

A Visual Analysis Tool to Explore Learned Representations in Transformers Models

exbert-assets icon exbert-assets

Contains large demo files needed to statically deploy examples for exBERT (https://github.com/bhoov/exbert)

exformer icon exformer

An Explorable Transformer. A lite version of exBERT

flybrain-nlp-vis icon flybrain-nlp-vis

Explore the word embeddings and concepts understood by a reprogrammed neural network of a fly

flyvec icon flyvec

A biologically inspired method to create sparse, binary word vectors

hamux icon hamux

Hierarchical Associative Memory User Experience

hiddenmambaattn icon hiddenmambaattn

Official PyTorch Implementation of "The Hidden Attention of Mamba Models"

june-vis icon june-vis

Visualization for the JUNE epidemic and intervention simulation tool

lcr-dicegame icon lcr-dicegame

Webppl implementation of the children's dicegame LCR (https://www.dicegamedepot.com/lcr-dice-game-rules/)

mae icon mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

musicpi icon musicpi

Hackathon 2018 Project for detecting faces on the raspberry pi

nbdev icon nbdev

Create delightful python projects using Jupyter Notebooks

ngd-vis icon ngd-vis

Understand the learning behavior of natural gradient descent vs SGD and other optimization methods

nlp-datasets icon nlp-datasets

Alphabetical list of free/public domain datasets with text data for use in Natural Language Processing (NLP)

nvae icon nvae

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

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.