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: They use flash storage, which... has electrons stored in tiny capacitor things where the charge persists for ages, or something.
gollark: There's a new ATX12VO standard which drops everything but 12V because it's not used much, apparently.
gollark: For now it'd be neat if there were actually good AR glasses available. Google Glass got killed off, and there was this company called North doing similar stuff but... Google bought them and killed them off too.
gollark: Brains are very adaptable, so perhaps you could just dump data into some neurons in some useful format and hope it learns to decode it.
gollark: I'd be *interested* in brain-computer-interface stuff, but it'll probably be a while before it develops into something useful and the security implications are very ææææaa.

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.