deep learning c

Preface At present, deep learning to grab enough eyeballs and attention, from the layout of major companies, to the springing out of a wave of start-up companies, and then to all kinds of popularization, in-depth analysis of the relevant public number, every day there are a large number of technology, paper interpretation related articles, blogs, etc., a variety of information such as flooding into our vis

Deep Learning paper notes (vii) Visualization of high-level features in depth networks Zouxy09@qq.com Http://blog.csdn.net/zouxy09 I usually read some papers, but the old feeling after reading will slowly fade, a day to pick up when it seems to have not seen the same. So want to get used to some of the feeling useful papers in the knowledge points summarized, on the one hand in the process of finishing, t

Deep Learning Source code Collection-Continuous update ... Zouxy09@qq.com Http://blog.csdn.net/zouxy09 Collected some source code for deep learning. The main is MATLAB and C + +, of course, there are python. Put it here and follow up with new updates that will continue. The table below is also welcome to be available

In depth learning, you often have to set the following data: Nepoch, iteration, BatchSize: BatchSize represents the number of batch gradients used when doing random gradient drops, that is, each time using batchsize data to update the parameters. 1 iteration equals to use BatchSize sample training once 1 Nepoch equals to use all samples for training once For example, the training set has 1000 samples, batchsize=10, then: after training the ent

= 1, 2.8.2 Anchor Boxes Algorithm For a previous lattice corresponding to a target, now a lattice not only corresponds to a target, but also for a anchor box, that is (grid cell, anchor Box), and then select the highest orthogonal. Take two anchor boxes for example, originally 3*3*8 become 3*3*2*8.9.YOLO Algorithm Before learning the basic elements of target detection, these elements can be combined to form the YOLO algorithm:-Input x (100*100*3), di

CNN began in the 90 's lenet, the early 21st century silent 10 years, until 12 Alexnet began again the second spring, from the ZF net to Vgg,googlenet to ResNet and the recent densenet, the network is more and more deep, architecture more and more complex, The method of vanishing gradient disappears in reverse propagation is also becoming more and more ingenious.　　　　 LeNet AlexNet Zf Vgg Googlenet ResNet Densenet

Recently, Google published in the Journal of the American Medical Council titled "Development and Validation of a deep learning algorithm for Detection of diabetic retinopathy in Reti NAL Fundus Photographs "is a deep learning algorithm that Google researchers have put forward to explain the signs of diabetic retinopat

First, it's up to the father of Ai, Turing. Turing once had a dream uninstall "computer and Intelligence" (1950) article, if one day, the computer can do, across the wall, you do not know the opposite and you communicate is a person or computer, then this computer has artificial intelligence. For the next half century, Ai has not developed much. Although the computer has the powerful memory and the data processing ability, but does not have the human cognition ability. For example, Wang, Meo

most important thing to know about OpenAI is to understand the frontiers of AI research.What is the research direction of Ai's frontier?OpenAI raised three points:-Training Generative Models-Algorithms for inferring algorithms from data-New approaches to reinforcement learningSo what do these three categories represent, respectively?Deep generative ModelsThe first type is oriented to the generation model, the main task is to generate new information,

feature algorithms, our goal is usually to isolate the variables that explain the observed data.Deep learning allows a computer to construct complex concepts through simpler concepts. (The examples in the comparison book can be understood clearly)The idea of learning the correct representation of data is a point of view for explaining deep

ObjectiveFor deep learning, novice I recommend to see UFLDL first, do not do assignment words, one or two nights can be read. After all, convolution, pooling what is not a particularly mysterious thing. The course is concise, sharply, and points out the most basic and important points.cs231n This is a complete course, the content is a bit more, although the course is computer vision, but 80% is the content

Second lecture: Simple word vector representation: Word2vec, Glove (easy word vector representations:word2vec, Glove)Reprint please specify the source and retention link "I love Natural Language processing": http://www.52nlp.cnThis article link address: Stanford University deep Learning and Natural language processing second: Word vectorRecommended Reading materials: paper1:[distributed representat

Document directory 1.1 how to restrict the use of the Polman machine (RBM) 1.2 restricted Polman machine (RBM) Energy Model 1.3 from energy model to probability 1.4 Maximum Likelihood 1.5 Sampling Method Used 1.6 introduction to Markov Monte Carlo References RBM for deep learning Reading Notes Statement: 1) I saw a statement from other blogs such as @ zouxy09, and the old man copied it. 2) This blo

Source: Michael Nielsen's "Neural Network and Deep leraning"This section translator: Hit Scir master Xu Zixiang (Https://github.com/endyul)Disclaimer: We will not periodically serialize the Chinese translation of the book, if you need to reprint please contact [email protected], without authorization shall not be reproduced."This article is reproduced from" hit SCIR "public number, reprint has obtained consent. " Using neural networks

matching is no longer effective, and then the OCR algorithm is difficult to parse the results.In recent years, The Deep Neural Network (DNN) has been proved to be a powerful recognition capability in the field of image recognition. The identification of single text is a typical classification problem. The usual practice is to train a deep neural network, the last layer of the network is divided into n cate

This paper summarizes some contents from the 1th chapter of Neural Networks and deep learning. Catalogue Perceptual device S-type neurons The architecture of the neural network Using neural networks to recognize handwritten numbers Towards Deep learning Perceptron (perceptrons)1. Fundament

Recently studied a few days of deep learning of the MATLAB Toolbox code, found that the author gives the source of the comments is very poor, in order to facilitate everyone to read, the code has been commented, share with you.Before reading the MATLAB Toolbox code, we recommend that you read a few CNN two classic materials, the convolutional neural Network MATLAB Toolbox Code understanding is very helpful,