Project details for Nen

Screenshot Nen - alpha -

by pascal - February 1, 2012, 20:23:49 CET [ Project Homepage BibTeX Download ]

view ( today), download ( today ), 0 subscriptions

Description:

Nen - Neural Network Implementation in Java

A 3-layer neural network for regression and classification with sigmoid activation function and command line interface similar LibSVM.

Quick Start: "java -jar nen.jar"

See this out-of-the-box comparison between LibSVM and Nen for a demonstration on several regression- and classification datasets.

Command-Line-Examples

Nen reads and writes LibSVM datasets (you will find some here).

Scale to -1..1
    java -jar nen.jar scale abalone abalone_scaled

Split into Test- and Train-Set
    java -jar nen.jar split abalone_scaled abalone_train abalone_test

Train Model
    java -jar nen.jar train abalone_train abalone_model

Predict Test-Set
    java -jar nen.jar predict abalone_test abalone_model abalone_predictions

Do Parameter Selection with Cross Validation
    java -jar nen.jar xval abalone_train abalone_model

Java-Example

// Create data (1000 data points, 8 attributes)
float[][] x=new float[1000][8];
float[][] y=new float[1000][1];

// Fill your data:
..............
..............

// Create an 8x16x1 regression network:
Nen nen=new Nen(Type.Regression,8,16,1);

// Train network 10000 steps, learnrate 0.005..0.0000001, not quiet:
nen.train(x,y,10000,0.005f,0.0000001f,false);

// Get Predictions for training set (true for threadsafe):
float[][] p=nen.get(x,true);

// Get Training Error (Mean-Squared)
float e=nen.getError(p,y);
Changes to previous version:

Initial Announcement on mloss.org.

BibTeX Entry: Download
Supported Operating Systems: Platform Independent
Data Formats: Libsvm
Tags: Neural Networks
Archive: download here

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.