期刊
ACM SIGPLAN NOTICES
卷 36, 期 2, 页码 26-36出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/609761.609765
关键词
neural programming language; compiler-decompiler; neural net definitions; hierarchical networks; superneuron
We present a language framework for handling arbitrarily complex neural computations. The software architecture - which we call an Artificial Neural Network Compiler for Hierarchical Organization (ANCHOR) facilitates network hierarchy and simpler sub-mappings, We define a Net Definition Language (NDL) which is implemented in object-oriented programming paradigm; a trained network is decompiled back into NDL. ANCHOR is configured around the concept of a Superneuron which is a generalized view of a neuron-processing element and designed using reuse of object-model. The indistinguishability between a superneuron and a neuron is employed in hierarchical nesting of superneurons, up to (theoretically) infinite depth within other superneurons as well as linear or tree-structured cascading. Hierarchical decomposition of simple boolean functions has been demonstrated as proof-of-concept.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据