登录
首页 » matlab » Deep learning_CNN DBN RBM

Deep learning_CNN DBN RBM

于 2018-12-18 发布 文件大小:14409KB
0 124
下载积分: 1 下载次数: 48

代码说明:

  运用深度学习模型实现图像的分类,主要包括卷积神经网络CNN和深信度网络DBN(Classification of images using deep learning model includes convolutional neural network CNN and belief network DBN.)

文件列表:

深度学习CNN%2BDBN%2BRBM\.travis.yml, 249 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caeapplygrads.m, 1219 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caebbp.m, 917 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caebp.m, 1011 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caedown.m, 259 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caeexamples.m, 754 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caenumgradcheck.m, 3618 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caesdlm.m, 845 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caetrain.m, 1148 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\caeup.m, 489 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\max3d.m, 173 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\scaesetup.m, 1937 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE\scaetrain.m, 270 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CNN\cnnapplygrads.m, 575 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CNN\cnnbp.m, 2141 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CNN\cnnff.m, 1774 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CNN\cnnnumgradcheck.m, 3430 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CNN\cnnsetup.m, 2020 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CNN\cnntest.m, 193 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CNN\cnntrain.m, 845 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CONTRIBUTING.md, 544 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\create_readme.sh, 744 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\data\mnist_uint8.mat, 14735220 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\DBN\dbnsetup.m, 557 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\DBN\dbntrain.m, 232 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\DBN\dbnunfoldtonn.m, 425 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\DBN\rbmdown.m, 90 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\DBN\rbmtrain.m, 1401 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\DBN\rbmup.m, 89 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\LICENSE, 1313 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nnapplygrads.m, 628 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nnbp.m, 1638 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nnchecknumgrad.m, 704 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nneval.m, 811 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nnff.m, 1849 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nnpredict.m, 192 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nnsetup.m, 1844 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nntest.m, 184 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nntrain.m, 2414 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN\nnupdatefigures.m, 1858 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\README.md, 8861 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\README_header.md, 2244 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\REFS.md, 950 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\SAE\saesetup.m, 132 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\SAE\saetrain.m, 308 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\tests\runalltests.m, 165 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\tests\test_cnn_gradients_are_numerically_correct.m, 552 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\tests\test_example_CNN.m, 981 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\tests\test_example_DBN.m, 1031 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\tests\test_example_NN.m, 3247 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\tests\test_example_SAE.m, 934 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\tests\test_nn_gradients_are_numerically_correct.m, 749 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\allcomb.m, 2618 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\expand.m, 1958 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\flicker.m, 208 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\flipall.m, 80 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\fliplrf.m, 543 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\flipudf.m, 576 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\im2patches.m, 313 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\isOctave.m, 108 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\makeLMfilters.m, 1895 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\myOctaveVersion.m, 169 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\normalize.m, 97 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\patches2im.m, 242 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\randcorr.m, 283 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\randp.m, 2083 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\rnd.m, 49 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\sigm.m, 48 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\sigmrnd.m, 126 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\softmax.m, 256 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\tanh_opt.m, 54 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\visualize.m, 1072 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\whiten.m, 183 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util\zscore.m, 137 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CAE, 0 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\CNN, 0 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\data, 0 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\DBN, 0 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\NN, 0 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\SAE, 0 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\tests, 0 , 2015-12-01
深度学习CNN%2BDBN%2BRBM\util, 0 , 2015-12-01
深度学习CNN%2BDBN%2BRBM, 0 , 2015-12-01

下载说明:请别用迅雷下载,失败请重下,重下不扣分!

发表评论

0 个回复

  • example source code
    MFC入门例子程序源代码-example source code
    2022-02-25 16:13:40下载
    积分:1
  • 你想没有硬件就跑μc OS吗,这里提供了一个虚拟的硬件设备,可以让你模拟真实的硬件环境...
    你想没有硬件就跑μc OS吗,这里提供了一个虚拟的硬件设备,可以让你模拟真实的硬件环境-You want to run there is no hardware μc OS you, here provides a virtual hardware device that lets you simulate real hardware environment
    2023-08-09 10:05:04下载
    积分:1
  • Flash书角折角广告代码
    可关闭的Flash右上角折角广告代码,鼠标点击一下会卷上去,再点击会向下展开,目前一些门户网站像新浪、网易仍在用的一种广告形式,这种广告效果要比弹窗、铺屏的体验好一些,用户可以有选择性的查看内容。
    2022-03-13 04:23:02下载
    积分:1
  • 循迹小车 proteus仿真仿真
    在proteus下可以实现小车的仿真,演示功能(It can realize the simulation of the car under the proteus, demonstration function)
    2021-05-09 22:58:34下载
    积分:1
  • Lammps-DPD-master
    说明:  对Lammps里的DPD package进行了稍微修改,可以进行电场和morse potential的计算。(Enable electrostatic interaction and morse potential of DPD package in Lammps)
    2020-06-26 05:45:06下载
    积分:1
  • JS缩略图大图切换,图片轮播代码
    JS缩略图大图切换,图片轮播代码,仿土豆网经典图片切换特效,鼠标点击缩略图,淡入淡出切换大图片,效果流畅似FLASH,若无鼠标点击,则自动轮播。
    2022-03-15 11:32:55下载
    积分:1
  • 这是一个有关货物管理的系统,它能对生活中的很多事情进行实施,很好的。...
    这是一个有关货物管理的系统,它能对生活中的很多事情进行实施,很好的。-This is a cargo management system, it lives in the implementation of a lot of things, very good.
    2022-02-02 09:21:08下载
    积分:1
  • 黑盒B-BOX 无限制版
    无限制版,极影工作室的看家产品之一,交易两个货币兑进行对冲。经过实际测试,EURUSD和GBPUSD的盈利效果最好,AUDUSD和NZDUSD不是很好。按理说这两组关联都不错才对,可能是测试期间行情所致,因为无法回测双币以上ea,实盘模拟测试。(One of the Housekeeping Products of Polarshadow Studio is trading two currencies to hedge against each other. After actual testing, EURUSD and GBPUSD have the best profitability, while AUDUSD and NZDUSD are not very good. It is reasonable to say that the correlation between the two groups is good, which may be due to the market during the test period, because it is impossible to retest the EA above two coins, a real-time simulation test.)
    2020-06-18 01:20:01下载
    积分:1
  • 新建文件夹
    锅炉模型,可以用于过程控制,模型预测控制,系统辨识(The boiler model can be used for process control, model predictive control and system identification.)
    2018-11-20 17:21:47下载
    积分:1
  • 基于STM32正弦波逆变器设计
    说明:  基于STM32正弦波逆变器设计,设计逆变器的一些有用文件(sinusoid; sinusoidal wave; sine wavenverter; dc-to-ac converter; dc-to-ac inverter)
    2019-01-21 10:35:26下载
    积分:1
  • 696524资源总数
  • 103827会员总数
  • 23今日下载