摘要: 稀疏编码在稀疏自编码算法中,我们试着学习得到一组权重参数 W(以及相应的截距 b),通过这些参数可以使我们得到稀疏特征向量 σ(Wx + b) ,这些特征向量对于重构输入样本非常有用。稀疏编码可以看作是稀疏自编码方法的一个变形,该方法试图直接学习数据的特征集。利用与此特征集相应的基向量,将学习得到的... 阅读全文
posted @ 2014-09-19 19:57 老姨 阅读(293) 评论(0) 推荐(0) 编辑
摘要: Sparse CodingSparse coding is a class of unsupervised methods for learning sets of over-complete bases to represent data efficiently. —— 过完备的基,无监督 The... 阅读全文
posted @ 2014-09-19 17:19 老姨 阅读(341) 评论(0) 推荐(0) 编辑
摘要: Pooling: Overview After obtaining features using convolution, we would next like to use them for classification. In theory, one could use all the extracted features with a classifier such as a sof... 阅读全文
posted @ 2014-09-19 16:12 老姨 阅读(467) 评论(0) 推荐(0) 编辑
摘要: Fully Connected NetworksIn the sparse autoencoder, one design choice that we had made was to "fully connect" all the hidden units to all the input uni... 阅读全文
posted @ 2014-09-19 15:44 老姨 阅读(221) 评论(0) 推荐(0) 编辑
摘要: Sparse Autoencoder RecapIn the sparse autoencoder, we had 3 layers of neurons: an input layer, a hidden layer and an output layer. In our previous des... 阅读全文
posted @ 2014-09-19 15:18 老姨 阅读(181) 评论(0) 推荐(0) 编辑
摘要: 转自:http://www.cnblogs.com/tornadomeet/archive/2013/03/25/2980357.html如果使用多层神经网络的话,那么将可以得到对输入更复杂的函数表示,因为神经网络的每一层都是上一层的非线性变换。当然,此时要求每一层的activation函数是非线性... 阅读全文
posted @ 2014-09-19 10:22 老姨 阅读(696) 评论(0) 推荐(0) 编辑
摘要: 字符串abs —— 输出字符串ascii码strvcat —— 把多个字符串横向连接成长字符串fprintf —— 把格式化的文本写到文件中或显示屏上int2str —— 整数转换成字符串num2str —— 数字转换成字符串sprintf —— 用格式控制,数字转换成字符串eval —— 作为一个... 阅读全文
posted @ 2014-09-18 20:30 老姨 阅读(464) 评论(0) 推荐(0) 编辑
摘要: VectorizationVectorization refers to a powerful way to speed up your algorithms. Numerical computing and parallel computing researchers have put decad... 阅读全文
posted @ 2014-09-18 16:18 老姨 阅读(369) 评论(0) 推荐(0) 编辑
摘要: Gradient checking and advanced optimizationIn this section, we describe a method for numerically checking the derivatives computed by your code to mak... 阅读全文
posted @ 2014-09-18 15:18 老姨 阅读(209) 评论(0) 推荐(0) 编辑
摘要: Neural NetworksWe will use the following diagram to denote a single neuron:This "neuron" is a computational unit that takes as input x1,x2,x3 (and a +... 阅读全文
posted @ 2014-09-18 10:41 老姨 阅读(280) 评论(0) 推荐(0) 编辑
摘要: OverviewIn the previous sections, you constructed a 3-layer neural network comprising an input, hidden and output layer. While fairly effective for MN... 阅读全文
posted @ 2014-09-17 17:05 老姨 阅读(204) 评论(0) 推荐(0) 编辑
摘要: In this section, we describe how you can fine-tune and further improve the learned features using labeled data. When you have a large amount of labele... 阅读全文
posted @ 2014-09-17 15:49 老姨 阅读(203) 评论(0) 推荐(0) 编辑
摘要: First, you will train your sparse autoencoder on an "unlabeled" training dataset of handwritten digits. This produces feature that are penstroke-like.... 阅读全文
posted @ 2014-09-16 17:04 老姨 阅读(290) 评论(0) 推荐(0) 编辑
摘要: the promise of self-taught learning and unsupervised feature learning is that if we can get our algorithms to learn from unlabeled data, then we can e... 阅读全文
posted @ 2014-09-16 16:26 老姨 阅读(508) 评论(0) 推荐(0) 编辑
摘要: Step 0: Initialize constants and parametersStep 1: Load dataStep 2: Implement softmaxCostImplementation Tip: Preventing overflows - in softmax regress... 阅读全文
posted @ 2014-09-16 15:25 老姨 阅读(422) 评论(0) 推荐(0) 编辑
摘要: This model generalizes logistic regression to classification problems where the class label y can take on more than two possible values. Softmax regression is a supervised learning algorithm, but ... 阅读全文
posted @ 2014-09-16 10:27 老姨 阅读(298) 评论(0) 推荐(0) 编辑
摘要: Step 0: Prepare dataStep 0a: Load dataThe starter code contains code to load a set of natural images and sample 12x12 patches from them. The raw patch... 阅读全文
posted @ 2014-09-14 21:44 老姨 阅读(531) 评论(0) 推荐(0) 编辑
摘要: Step 0: Load dataThe starter code contains code to load 45 2D data points. When plotted using the scatter function, the results should look like the f... 阅读全文
posted @ 2014-09-14 20:41 老姨 阅读(499) 评论(0) 推荐(0) 编辑
摘要: The goal of whitening is to make the input less redundant; more formally, our desiderata are that our learning algorithms sees a training input where ... 阅读全文
posted @ 2014-09-14 16:59 老姨 阅读(399) 评论(0) 推荐(0) 编辑
摘要: http://deeplearning.stanford.edu/wiki/index.php/PCAPrincipal Components Analysis (PCA) is a dimensionality reduction algorithm that can be used to sig... 阅读全文
posted @ 2014-09-14 16:12 老姨 阅读(214) 评论(0) 推荐(0) 编辑