Skip to content
forked from jjfeng/spinn

Sparse-input neural networks

Notifications You must be signed in to change notification settings

binfnstats/spinn

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Sparse-Input Neural Network

Jean Feng and Noah Simon. "Sparse-Input Neural Networks for High-dimensional Nonparametric Regression and Classification." https://arxiv.org/abs/1711.07592

Note: For the latest iteration of this work, see Jean Feng and Noah Simon. "Ensembled sparse-input hierarchical networks for high-dimensional datasets." https://arxiv.org/abs/2005.04834

Installation:

Install Tensorflow (python).

Code was run using python 3.4.3

Primary files:

  • read_data.py: make a dataset in the correct format
  • fit_spinn.py: main file for fitting SPINN!
  • fit_<other_methods>.py: fit using other methods

Simulations and data analyses

Each folder specifies the simulation or data analyses. Each folder is associated with its own plotting code via plot_<folder_name>.py. To run the simulations/data analyses, use scons.

Note: process_peptide_binding.py: Processes data downloaded from https://github.com/openvax/mhcflurry

About

Sparse-input neural networks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%