{"@context":"https://w3id.org/codemeta/3.0","@type":"SoftwareSourceCode","identifier":"pkg:hackage/neural","name":"neural","description":"The goal of neural is to provide a modular and flexible neural network library written in native Haskell.\n\nFeatures include\n\ncomposability via arrow-like instances and\npipes,\n\nautomatic differentiation for automatic gradient descent/ backpropagation training\n(using Edward Kmett's fabulous ad library).\n\nThe idea is to be able to easily define new components and wire them up in flexible, possibly\ncomplicated ways (convolutional deep networks etc.).\n\nFour examples are included as proof of concept:\n\nA simple neural network that approximates the sine function on [0,2 pi].\n\nAnother simple neural network that approximates the sqrt function on [0,4].\n\nA slightly more complicated neural network that solves the famous\nIris flower problem.\n\nA first (still simple) neural network for recognizing handwritten digits from the equally famous\nMNIST database.\n\nThe library is still very much experimental at this point.","version":"0.3.0.1","softwareVersion":"0.3.0.1","license":"https://spdx.org/licenses/MIT","codeRepository":"https://github.com/brunjlar/neural","issueTracker":"https://github.com/brunjlar/neural/issues","url":"https://github.com/brunjlar/neural","keywords":["library","machine-learning","mit","program","Propose Tags"],"programmingLanguage":{"@type":"ComputerLanguage","name":"Haskell"},"maintainer":[{"@type":"Person","name":"lbrunjes"}],"author":[{"@type":"Person","name":"lbrunjes"}],"copyrightHolder":[{"@type":"Person","name":"lbrunjes"}],"dateCreated":"2016-06-06","dateModified":"2017-07-27","datePublished":"2017-07-27","copyrightYear":2016,"downloadUrl":"https://hackage.haskell.org/package/neural-0.3.0.1/neural-0.3.0.1.tar.gz","applicationCategory":"hackage","runtimePlatform":"hackage","developmentStatus":"active","sameAs":["https://hackage.haskell.org/package/neural"],"https://www.w3.org/ns/activitystreams#likes":122,"https://forgefed.org/ns#forks":13}