搜索资源列表
TOTO_NeuralNetwork_v2
- 全手工Java书写的完全面向对象结构的人工神经网络，现版本，仅实现BP神经网络以及普通梯度下降法，但结构精炼，易于扩展，本人正在书写稀疏自编码用于图像处理，但本版本尚未涵盖。将在以后的版本中上传。（附带CSV输入）-Neural Network Programmed by JAVA, the key contribution of this Project is 100 OO based, readers can easily fig
sparseae_exercise
- 该文档包含了深度学习的典型模型稀疏自编码的程序和代码-this document contain sparseae exercise of deep learning network
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.
sparseae_exercise_finished
- 稀疏自编码器，UFLDL教程中的练习代码，已经完成了需要补充的代码-Sparse Autoencoder
Autoencoder_Code
- 深信度网络中的自编码部分，包括受限玻尔兹曼机训练，BP算法反向微调，深度学习入门学习材料！-Convinced of the network of self-coding parts, including Restricted Boltzmann Machine training, BP algorithm reverse trimming, deep learning introductory learning materials!
stackedAE
- 堆栈自编码，通过两个稀疏自编码的堆叠和softmax分类模型，实现手写体的分类。-Stack self-encoding, since encoding by two sparse stack and softmax classification model to classify handwriting.
Sparse-Autoencoder
- 稀疏自编码是构成堆栈式自编码的基础，通过稀疏自编码可以提取图像的边缘特征。-Sparse coding constitute the basis of the stack self-encoded by sparse coding can be extracted the edge feature of the image.
self-taught-learning
- 自主学习把稀疏自编码器和分类器实现结合。先通过稀疏自编码对无标签的5-9的手写体进行训练得到最优参数，然后通过前向传播，得到训练集和测试集的特征，通过0-4有标签训练集训练出softmax模型，然后输入测试集到分类模型实现分类。-Independent Learning the encoder and the sparse classifiers achieve the combination. First through spars
ex6SA
- 本程序实现了一个简单的稀疏自编码器，能够获得图像的权重。-The program implements a simple sparse the encoder, the right to be able to obtain an image of the weight.
sparse-autoencoding
- UFLDL的稀疏自编码样例程序.使用matlab语言编写-sparse auto-encoding program using matlab in UFLDL
sparseae_yjy
- 本程序主要讨论了稀疏自编码的仿真实现，并且对数据进行了可视化处理-This procedure is mainly discussed in the simulation of sparse since encoding, and the data were visualized processing
DLT
- Online Robust Non-negative Dictionary Learning for Visual Tracking , Naiyan Wang and Dit-Yan Yeung, NIPS2013，论文代码，实现自编码器快速跟踪算法- Online Robust Non-negative Dictionary Learning for Visual Tracking , Naiyan Wang and Dit-Ya
starter
- 基于深度学习的稀疏自编码器，对图像特征进行提取，然后分类-Extraction the encoder based on sparse feature depth study
Exercise10-Sparse-Coding
- 在windows下的MATLAB实现的深度学习的稀疏自编码器的代码-（windows） sae inMATLAB
sparseae
- 用matlab代码实现的稀疏自编码器，通过可视化步骤，可以看到稀疏编码提取出来的她特征。- sparse autoencoder written by matlab, through visualization step, you can find the features extracted by sparse coding .
sparseAutoencoder
- 关于神经网络中稀疏自编码的原理说明，该资料为英文原文-The principle of sparse self coding on the neural network, the information is in English
SAE
- 深度学习中的重叠自编码型深度学习网络工具箱，可直接输入数据运行。-deeplearning toolbox of SAE
Sparse-Autoencoder
- 神经网络稀疏自编码器的实现；从给定的很多张自然图片中截取出大小为8*8的小patches图片共10000张，现在需要用sparse autoencoder的方法训练出一个隐含层网络所学习到的特征。-Sparse neural networks since implementation of the encoder interception of a size of 8* 8 picture small patches given a
stacked-autoencoder
- 基于两层的层叠自编码的深度学习模型，前两层用于特征提取，再加一个Softmax分类器用于分类-Two stacked the depth of learning coding model based on the first two levels for feature extraction, coupled with a classifier for classifying Softmax
melppaper6
- 为了提高深度模型的编码重构性能,本文为传统对比散度(Contrastive divergence,CD)添加了基于交叉熵的重构误差约束。利用改进后的算法训练了重构性深度自编码机(Reconstructive deep au-to-encoder,RDAE),并用 RDAE 替换混合激励线性预测编码(Mixed excitation linear prediction, MELP)语音编码器中 LSF 参数的矢量量化方法。测试结果表明,改