搜索资源列表
CudaConv
- 功能还不大清楚，不是本人开发的-Convolution of an arbitrary 1D complex signal with an arbitrary filter kernel
linear-convolution-code
- 用C++语言编写的线性卷积代码。可用于小波变换及其它图像应用。-The linear convolution code written C++ language. Can be used for the wavelet transform and other image applications.
word-recognition-and-nerual-networks
- 基于卷积神经网络的字符识别技术，较好的算法！！神经网络、-Convolution-based neural network character recognition technology, better algorithm! ! Neural network,
Convolution_GPU
- This project implement the convolution neural network on GPU. This reduce much time for training process. This project was written in C# and cuda
caffe
- 一种设计的卷积神经网络用于图像特征的快速提取，并可以根据环境自行选择是否使用GPU-Design of a convolution neural networks for image feature extraction fast, and you can choose whether to use the GPU itself according to the environment
mangjiejuanji
- 信号处理的盲源分离算法，用于信号卷积混合盲分离，供大家参考一下。-Blind Source Separation of signal processing algorithms for signal convolution Blind separation, for your reference.
convolutionalRBM.m-master
- 深度学习方法中的卷积受限玻尔兹曼机的必备学习源，有助于了解方法原理。-Convolution restricted boltzmann machine in deep learning approach, a necessary source of learning, helps to understand the method principle
cdbn
- 卷积的DBN和RBM，包含详细的代码。可运行，并与论文结果相差不大，适合初学者借鉴。-DBN and RBM convolution, contains a detailed code. Can run, and with little difference between the results of the paper, suitable for beginners reference.
CDBN-master
- 实现了卷积受限玻尔兹曼机（深度学习的一个重要算法），包括C++和matlab版本-Restricted Boltzmann realized convolution machine (depth study of an important algorithm), including C++ and matlab version
[codes]NIN
- 是2014年的cnn上的一个变化的网络，将卷积层与池化层之间的线性关系变成1×1的卷积层的非线性关系，名为network in network-Is a change in the 2014 cnn on the network layer of the linear convolution and pooled into a non-linear relationship between the layers 11, convolution layer, called the network
CNN-with-three-pooling-strategy
- 这是matlab的代码，将cnn进行三次池化的代码，可以作为学习卷积神经网络的入门例子-This is a matlab code that will perform three pooled cnn code can be used as a convolution neural network learning introductory example
cnn_linear_max-master
- 一个简单的卷积神经网络与线性神经元。 结构:输入- >卷积- > max池- >卷积- > max池- >完全连接。 编译c++马克斯池功能首先输入“墨西哥人MaxPooling.cpp”。 数据可以在http://ai.stanford.edu/下载~ amaas /数据/ data.zip 可以在http://ufldl.stanford.edu/wiki/index.php/Using_the_MNIST_Dataset下载的数据加载函数
Convolution
- 数字图像处理中卷积运算，做图像处理的可以用。-Convolution operation in digital image processing, image processing can be used.
MNIST_theano
- 利用theano库完成MNIST手写识别，包括稀疏自编码机，多层感知机，卷积神经网络-using the theano to complete the handwriting congnization in MNIST ,include Denoising AutoEncoder,MLP,Convolution Neutral Network.
workstandard
- 深度信念网络带有限制玻耳兹曼机和反向传播网络以及卷积神经网络和子编码网络-Network with a limited depth of faith Boltzmann machine and reverse the spread of networks and convolution coding neural networks and sub-networks
cnn_vs2012
- 基于Mnist库的手写数字识别的C++源代码，用卷积神经网络实现-Handwritten numeral recognition Mnist library C++ source code, using convolution neural network
CNN
- 深度学习中卷积神经网络，实现手写数字的分类，其中包含网络的初始化，训练，测试三个模块。包含mnist_uint8.mat文件，CNN入门学习程序。-Convolution depth study neural networks, digital handwritten classification, which includes the network initialization, training, testing three modules. Files contain mnist_uin
cnn
- 用卷积神经网络实现字母图像的识别，里面包含数据集，可直接使用-Achieve recognition letters image convolution neural network, which includes data collection, can be used directly
CNN
- 用 卷积神经网络进行手写字符 识别,内含mnist训练集-Handwritten character recognition, containing mnist convolution neural network training set
convolution-nn
- 卷积神经网络源代码，visual studio可以运行的！mnist手写库的idx-ubyte格式的数据在里面，原图片再另一个工程里-convolution neural network