backy 0.2.1

  • README.md
  • Installing
  • Versions
  • 0

backy #

Backy is a neural network which is using the backpropagation algorithm. (Written in Googles Dart). Please report all errors you can find to me.

How to #

The Neuron The neuron defines how the output is computed and in what range...

The Neural Network: #

It can be instanciated with any number of layer dimensions. For example: [2, 3, 1] which produces a net with 3 layers. The input layer has two inputs and the output layer has 1 output neuron. The hidden layer has 3 neurons.

Train the network #

Use the "train"-method to tell the net what you expect from a certain input. net.train(<input>, <expected>);

e.g. train an XOR network:

  net.train([-1, -1], [ 1]);
  net.train([-1,  1], [-1]);
  net.train([ 1, -1], [-1]);
  net.train([ 1,  1], [ 1]);

Use the Network #

Once the network is trained, you can use it and it will return the output:

<expected> = net.use(<input>);

print(net.use([-1, 1])); // prints probably: [-.9988, .9988]

A working example: #

The network needs usually many trainingsteps in orderto find the right weights and therefore the solution. Use the trainer in order to train backy more comfortably.

  1. Imagine the trainer as a personal trainer for a student.
  2. You tell the trainer what he should train the student.
  3. And he will repeat the training until the student produces the expected answers, or until a maximum of trainingrounds has been exceeded.
// 1.
  var neuron  = new TanHNeuron(); // returnes floatingpoint values between -1 and 1
  var student = new Backy([2, 2, 1], neuron);
  var trainer = new Trainer(backy: student, maximumReapeatingCycle: 200, precision: .1);

// 2. Add the pattern whcih the network should learn
  trainer.addTrainingCase([-1,-1], [-1]);
  trainer.addTrainingCase([-1, 1], [-1]);
  trainer.addTrainingCase([ 1,-1], [-1]);
  trainer.addTrainingCase([ 1, 1], [ 1]);

// 3. train all the traininCases up to 300 times and be satisfied with a precision of .1
  print(trainer.trainOnlineSets()); // prints number loops it took to learn all trainingcases

// 4. After that you can use the neural network
  print(student.use([-1,-1]));
  print(student.use([-1, 1]));
  print(student.use([ 1,-1]));
  print(student.use([ 1, 1]));

Use this package as a library

1. Depend on it

Add this to your package's pubspec.yaml file:


dependencies:
  backy: ^0.2.1

2. Install it

You can install packages from the command line:

with pub:


$ pub get

Alternatively, your editor might support pub get. Check the docs for your editor to learn more.

3. Import it

Now in your Dart code, you can use:


import 'package:backy/backy.dart';
  
Version Uploaded Documentation Archive
0.2.1 Sep 1, 2013 Go to the documentation of backy 0.2.1 Download backy 0.2.1 archive
0.2.0 Sep 1, 2013 Go to the documentation of backy 0.2.0 Download backy 0.2.0 archive
0.1.0 Aug 24, 2013 Go to the documentation of backy 0.1.0 Download backy 0.1.0 archive
Popularity:
Describes how popular the package is relative to other packages. [more]
0
Health:
Code health derived from static analysis. [more]
--
Maintenance:
Reflects how tidy and up-to-date the package is. [more]
--
Overall:
Weighted score of the above. [more]
0
Learn more about scoring.

The package version is not analyzed, because it does not support Dart 2. Until this is resolved, the package will receive a health and maintenance score of 0.

Analysis issues and suggestions

Support Dart 2 in pubspec.yaml.

The SDK constraint in pubspec.yaml doesn't allow the Dart 2.0.0 release. For information about upgrading it to be Dart 2 compatible, please see https://www.dartlang.org/dart-2#migration.

Maintenance issues and suggestions

Make sure dartdoc successfully runs on your package's source files. (-10 points)

Dependencies were not resolved.