代码搜索：Neuron
找到约 763 项符合「Neuron」的源代码
代码结果 763
www.eeworm.com/read/140283/5793077
h twolayernetwork.h
#ifndef _TWOLAYERNETWORK_H
#define _TWOLAYERNETWORK_H
#include "MultiLayerNetwork.h"
namespace annie
{
/** Two layered networks are very commonly used. This is basically a
* multi-layer perceptro
www.eeworm.com/read/127819/5994505
h netiodata.h
/***************************************************************************
netiodata.h - description
-------------------
copyright
www.eeworm.com/read/127819/5994507
h povray.h
/***************************************************************************
povray.h - description
-------------------
begin
www.eeworm.com/read/127819/5994522
h layer.h
/***************************************************************************
layer.h - description
-------------------
begin
www.eeworm.com/read/127819/5994525
h functionlookup.h
/***************************************************************************
functionlookup.h - description
-------------------
copyright
www.eeworm.com/read/127819/5994540
cpp network.cpp
/***************************************************************************
network.cpp - description
-------------------
copyright
www.eeworm.com/read/489292/6477987
java topologymodel.java
/**
* Copyright (c) 2006, Seweryn Habdank-Wojewodzki
* Copyright (c) 2006, Janusz Rybarski
*
* All rights reserved.
*
* Redistribution and use in source and binary forms,
* with or without mod
www.eeworm.com/read/482140/6628476
java layer.java
/**
* Layer
* Copyright 2005 by Jeff Heaton(jeff@jeffheaton.com)
*
* Example program from Chapter 2
* Programming Neural Networks in Java
* http://www.heatonresearch.com/articles/series/1/
*
*
www.eeworm.com/read/259886/11759443
m applin1.m
%APPLIN1 Linear prediction.
% Mark Beale, 12-15-93
% Copyright 1992-2002 The MathWorks, Inc.
% $Revision: 1.14 $ $Date: 2002/04/14 21:22:30 $
clf;
figure(gcf)
echo on
% NEWLIND - So
www.eeworm.com/read/259886/11759490
m demosm2.m
%% A Two-dimensional Self-organizing Map
% As in DEMOSM1, this self-organizing map will learn to represent different
% regions of the input space where input vectors occur. In this demo, however,