cshewmake2 Goto Github PK

2022

The official webpage for the 2022 Workshop on Symmetry and Geometry in Neural Representations

chime

COVID-19 Hospital Impact Model for Epidemics

cone-classification

The use of adaptive optics scanning laser ophthalmoscopy (AOSLO) to probe color perception at the individual cone level has become increasingly of interest in the vision science community. Such experiments are enabled by having individual subjects' cone classification map which is inferred through a separate cone classification process. Thus, there is need for fast, accurate, and accessible cone classification algorithms. For our project, we propose a densitometry method for estimating cone types using an AOSLO and an algorithm for optical feedback which exploits differences in cone absorption spectra. We hope that this project will improve on or complement the state-of-the-art densitometry cone classification methods.

conserved_quantities

Learning Conserved Quantities of ODE Attractors

esc_message_passing

geomstats

Computations and statistics on manifolds with geometric structures.

geomstats.github.io

Geomstats documentation

landclassification

mcmcmusic

A project experimenting with generating music using a Markov Chain Monte Carlo method

p5_testing

pyrt_wrapper

pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

react-sparse-coding

reading-list

A collection of resources related with geometry of representations in the brain, deep networks and beyond. (NeurReps Workshop - NeurIPS 2022)

scipy_proceedings

Tools used to generate the SciPy conference proceedings

sgi-introduction-course

A course for getting started with geometry processing using MATLAB and gptoolbox

site_template

Code that'll help you kickstart a personal website that showcases your work as a software developer.

sonic_manifolds

Exploring sound spaces and manifold learning!

tfmusicaudioencoder

An Autoencoder for WAV files

units_in_a_ring

wordnet_poincare

Implementation of "Poincaré Embeddings for Learning Hierarchical Representations" by Nickel and Kiela, 2017, https://arxiv.org/pdf/1705.08039.pdf