hinton neural networks

Reference: Artificial neural network-Han Liqun pptlooking at some of the language models based on neural networks, compared with traditional language models, there is no need for additional smoothing algorithms In addition to the amount of computational effort, which makes them surprisingly effective. These networks c

IntroductionIn the previous chapter, although the BP neural network has made great progress, but it has some unavoidable problems, one of which is more confused is the problem of local optimal solution. It is risky to touch only those things you already like, that you may be involved in a self-centered whirlpool that ignores anything that is slightly different from your standards, even if you would have liked it. This phenomenon is known as t

visual comprehension of convolutional neural networks The first to suggest a visual understanding of convolutional neural Networks is Matthew D. Zeiler in the visualizing and understanding convolutional Networks. The following two blog posts can help you understand this a

in the second layer.The formula is:The original image is mapped to, 0-255, here is generally set to 8, function h is a step function. , which indicates the number of filters in the second layer.For each output matrix of the first layer, it is divided into B block, calculate the histogram information of each block, then cascade the histogram features of each block, and finally get the Block expansion histogram feature:Overlapping and non-overlapping block patterns can also be used for histogram

next layer, each neuron only related to the K values of the previous layer.However, the introduction of the concept of weight sharing, the model is further simplified to achieve: the number of weight is only related to the size of kernel. For kernel and Weight sharing, it can be understood that there is no fixed connection between the L layer and the L-1 layer, but rather dynamic binding, where there is a small window between the two layers, called kernel. A small portion of the original image

5.1 Cost FunctionSuppose the training sample is: {(x1), Y (1)), (x (2), Y (2)),... (x (m), Y (m))}L = Total No.of layers in NetworkSl= no,of units (not counting bias unit) in layer LK = number of output units/classesThe neural network, L = 4,S1 = 3,s2 = 5,S3 = 5, S4 = 4Cost function for logistic regression:The cost function of a neural network:　　　5.2 Reverse Propagation Algorithm backpropagationA popular ex

This is a creation in Article, where the information may have evolved or changed. Http://pan.baidu.com/s/1hr3kxog http://download.csdn.net/detail/nehemiah666/9472669 There are nature on the paper, I translated the Chinese version, and recorded a narration alphago working principle of the video, is a summary of the principle of alphago work. Here is the summary section: For artificial intelligence, Weiqi has always been considered the most challenging classic game, due to its huge search space

theoretical knowledge : Deep learning: 41 (Dropout simple understanding), in-depth learning (22) dropout shallow understanding and implementation, "improving neural networks by preventing Co-adaptation of feature detectors "Feel there is nothing to say, should be said in the citation of the two blog has been made very clear, direct test itNote :1. During the testing phase of the model, the output of the hid

We can pass the torch. NN package constructs a neural network. Now we've learned that AUTOGRAD,NN defines models based on Autograd and differentiates them.Onenn.Module模块由如下部分构成：若干层，以及返回output的forward(input)方法。For example, this diagram depicts a neural network for digital Image classification:This is a simple feedforward (feed-forward) network that reads input content, each layer accepts inputs from the prev

Discovery modeThe linear model and the neural network principle and the goal are basically consistent, the difference manifests in the derivation link. If you are familiar with the linear model, the neural network will be well understood, the model is actually a function from input to output, we want to use these models to find patterns in the data, to discover the existence of the function dependencies, of

Bowen content reproduced: http://blog.csdn.net/ybdesire/article/details/51792925 Optimization Algorithm To solve the optimization problem, there are many algorithms (the most common is gradient descent), these algorithms can also be used to optimize the neural network. Each depth learning library contains a large number of optimization algorithms to optimize the learning rate, so that the network with the fastest training times to achieve optimal, bu

I. Documentation names and authorsconvolutional neural Networks at Constrained time COST,CVPR two. Reading timeJune 30, 2015Three. Purpose of the documentThe author hopes to improve the accuracy of CNN by modifying the model depth and the parameters of the convolution template, while maintaining the computational complexity. Through a lot of experiments, the author finds the importance of different paramete

Some methods of himself analysis (II.) will be supplemented in the future. --by weponCombined with the literature "deep Learning for computer Vision", here are some points of attention and questions about convolutional neural networks. The excitation function is to choose a nonlinear function, such as tang,sigmoid,rectified liner. In CNN, Relu is used more because: (1) Simplifying BP calculations and (2