Giter Site home page Giter Site logo

zahraatashgahi / neurofs Goto Github PK

View Code? Open in Web Editor NEW
6.0 1.0 1.0 1.18 MB

[TMLR] Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks

Home Page: https://openreview.net/forum?id=GcO6ugrLKp

Python 100.00%
deep-learning dynamic-sparse-training efficiency feature-selection high-dimensional-data keras neural-networks python sparse-neural-networks sparse-training

neurofs's Introduction

NeuroFS

This repository contains code for the paper, "Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks" by Zahra Atashgahi, Xuhao Zhang, Neil Kichler, Shiwei Liu, Lu Yin, Mykola Pechenizkiy, Raymond Veldhuis, Decebal Constantin Mocanu, which is accepted by TMLR (https://openreview.net/forum?id=GcO6ugrLKp).

Methodology

algorithm

Feature Selection on the MNIST dataset

MNIST

How to run

K=50
seed=0 
dataset=coil20 # USPS isolet  har MNIST Fashion-MNIST BASEHOCK (batch size = 100) arcene Prostate_GE SMK GLA-BRA-180 (batch size = 20) 

python3 ./code/main.py   --dataset_name $dataset \
		--model "NeuroFS" --K $K\
		--batch_size 100 --lr 0.01 --epochs 100\
		--zeta_in 0.2 --zeta_hid 0.3 --epsilon 30\
		--num_hidden 1000 --seed $seed --wd 0.00001\
		--gradient_addition --frac_epoch_remove 0.65 \
		--activation "tanh" 

Requirements

Following Python packages have to be installed before executing the project code:

keras                     2.3.1           
keras-gpu                 2.3.1                   
matplotlib                3.5.1              
numpy                     1.21.5         
python                    3.7.13            
python-dateutil           2.8.2              
scikit-learn              1.0.2                 
scipy                     1.7.3          
tensorflow                1.14.0            
tensorflow-gpu            1.14.0                  

Acknowledgements

Starting of the code is the Sparse Evolutionary Training (SET) algorithm which is available at: https://github.com/dcmocanu/sparse-evolutionary-artificial-neural-networks

Citation

@article{
atashgahi2022supervised,
title={Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks},
author={Zahra Atashgahi and Xuhao Zhang and Neil Kichler and Shiwei Liu and Lu Yin and Mykola Pechenizkiy and Raymond Veldhuis and Decebal Constantin Mocanu},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2022},
url={https://openreview.net/forum?id=GcO6ugrLKp},
note={}
}

Contact

email: [email protected]

neurofs's People

Contributors

zahraatashgahi avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

matthijskeep

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.