代码搜索：MLP
找到约 754 项符合「MLP」的源代码
代码结果 754
www.eeworm.com/read/469416/6976372
m mlp.m
function net = mlp(nin, nhidden, nout, outfunc, prior, beta)
%MLP Create a 2-layer feedforward network.
%
% Description
% NET = MLP(NIN, NHIDDEN, NOUT, FUNC) takes the number of inputs,
% hidden
www.eeworm.com/read/145776/12703072
m mlp.m
%MLP Multilayer Perceptron algorithm
%
% 'ifile.mat' - input file containing:
% Nr - members of ensemble
% dim - iterations
% Nneur - number of neurons
% Sx - standard deviation
www.eeworm.com/read/143706/12849631
m mlp.m
function net = mlp(nin, nhidden, nout, outfunc, prior, beta)
%MLP Create a 2-layer feedforward network.
%
% Description
% NET = MLP(NIN, NHIDDEN, NOUT, FUNC) takes the number of inputs,
% hidden units
www.eeworm.com/read/143686/12850841
class mlp.class
www.eeworm.com/read/143686/12850867
java mlp.java
/**BackProp - a backpropagation neural network class 4/98 by
* Jason Tiscione.
* Copyright (c) 1998. All Rights Reserved. You have a non-exclusive,
* royalt
www.eeworm.com/read/140851/13059016
m mlp.m
function net = mlp(nin, nhidden, nout, outfunc, prior, beta)
%MLP Create a 2-layer feedforward network.
%
% Description
% NET = MLP(NIN, NHIDDEN, NOUT, FUNC) takes the number of inputs,
% hidden
www.eeworm.com/read/138798/13212070
m mlp.m
function net = mlp(nin, nhidden, nout, outfunc, prior, beta)
%MLP Create a 2-layer feedforward network.
%
% Description
% NET = MLP(NIN, NHIDDEN, NOUT, FUNC) takes the number of inputs,
% hidden
www.eeworm.com/read/323831/13314041
h mlp.h
// Copyright (C) 2003 Ronan Collobert (collober@idiap.ch)
//
// This file is part of Torch 3.
//
// All rights reserved.
//
// Redistribution and use in source and binary forms,
www.eeworm.com/read/303999/13805066
m mlp.m
clc;
clear all;
InputFilename = 'aa.wav'; %change it according to your wave files
[inspeech, Fs, bits] = wavread(InputFilename); % read the wavefile
Order = 10; % order of the model used
www.eeworm.com/read/302326/13837636
m mlp.m
%MLP Multilayer Perceptron algorithm
%
% 'ifile.mat' - input file containing:
% Nr - members of ensemble
% dim - iterations
% Nneur - number of neurons
% Sx - standard deviation