- 授权协议: MIT
- 开发语言: JavaScript
- 操作系统: 跨平台
- 软件首页: http://caza.la/synaptic
- 软件文档: https://github.com/cazala/synaptic/wiki
- 官方下载: https://github.com/cazala/synaptic
软件介绍
Synaptic.js 是一个用于 node.js 和浏览器的 JavaScript 神经网络库,可以构建和训练基本上任何类型的一阶甚至二阶神经网络。
该项目内置了 4 种经典的神经网络算法:多层感知器(multilayer perceptrons)、长短期记忆网络(multilayer long-short term memory networks)、液体状态机(Liquid State Machine)、Hopfield神经网络。使用 Synaptic.js ,你可以轻松测试和比较不同体系结构的性能。
Demo
creature.js
var synaptic = require('synaptic'); this.network = new synaptic.Architect.Perceptron(40, 25, 3);
world.js
creatures.forEach(function(creature) { // move var input = []; for (var i in creatures) { input.push(creatures[i].location.x); input.push(creatures[i].location.y); input.push(creatures[i].velocity.x); input.push(creatures[i].velocity.y); } var output = creature.network.activate(input); creature.moveTo(output); // learn var learningRate = .3; var target = [ targetX(creature), targetY(creature), targetAngle(creature)]; creature.network.propagate(learningRate, target); });
The Practice of Programming
Brian W. Kernighan、Rob Pike / Addison-Wesley / 1999-2-14 / USD 49.99
With the same insight and authority that made their book The Unix Programming Environment a classic, Brian Kernighan and Rob Pike have written The Practice of Programming to help make individual progr......一起来看看 《The Practice of Programming》 这本书的介绍吧!