Neuroph

Neuroph is an object-oriented artificial neural network framework written in Java. It can be used to create and train neural networks in Java programs. Neuroph provides Java class library as well as GUI tool easyNeurons for creating and training neural networks.

Neuroph
Stable release
2.94 / June 20, 2017 (2017-06-20)
Written inJava
PlatformJava platform
Available inEnglish
TypeNeural network
LicenseApache License
Websiteneuroph.sourceforge.net

It is an open-source project hosted at SourceForge under the Apache License. Versions before 2.4 were licensed under LGPL 3, from this version the license is Apache 2.0 License.

Features

Neuroph's core classes correspond to basic neural network concepts like artificial neuron, neuron layer, neuron connections, weight, transfer function, input function, learning rule etc. Neuroph supports common neural network architectures such as Multilayer perceptron with Backpropagation, Kohonen and Hopfield networks. All these classes can be extended and customized to create custom neural networks and learning rules. Neuroph has built-in support for image recognition.

gollark: Greetings.
gollark: Anyway, you can track movement by hooking the functions which do it. There are libraries for this.
gollark: Suffer, generally.
gollark: They were writing their own constrained programming language to make it work, accursedly.
gollark: Heav had issues with this.

See also

References


    This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.