CNN
xiaomiguan
happy
展开
-
Deep learning:四十一(Dropout简单理解)
前言 训练神经网络模型时,如果训练样本较少,为了防止模型过拟合,Dropout可以作为一种trikc供选择。Dropout是hintion最近2年提出的,源于其文章Improving neural networks by preventing co-adaptation of feature detectors.中文大意为:通过阻止特征检测器的共同作用来提高神经网络的性能。本篇博文就是按照这转载 2015-11-24 19:10:01 · 382 阅读 · 0 评论 -
striving for simplicity:the all convolutional net
1 Why the author want to write this paper? the basic architecture of convolutional neural networks(CNNs) mainly consists of convolutional layer, ReLU layer, pooling layer and full connection layer. I原创 2015-12-23 01:07:38 · 1373 阅读 · 0 评论 -
基于深度学习的图像语义分析及其应用
本文 转自“火光摇曳”博客:语义分析的一些方法(三),主要论述了基于深度学习方法的图像语义分析,包括图片分类、图片搜索、图片标注(image2text、image2sentence),以及训练深度神经网络的一些tricks,并介绍语义分析方法在腾讯广点通上的实际应用。以下为全文内容:3 图片语义分析3.1 图片分类图片分类是一个最基本的图片语义分析方法。基于深度转载 2015-11-20 18:18:44 · 3933 阅读 · 1 评论 -
Convolutional Networks
CNN原创 2015-11-19 20:07:24 · 463 阅读 · 0 评论 -
Maxout
Reading Paper-Network In Network(1)-MaxoutThe maxout is designed to solve the problem that the representations that achieve good abstraction are generally highly nonlinear functions of the input data.原创 2015-11-25 00:51:51 · 605 阅读 · 0 评论 -
Deep learning-contrast normalization
Deep learning-contrast normalization In order to reduce unit’s activation if neighbor’s unites are also active and create competition between feature maps, we apply the contrast normalization to deal原创 2015-11-26 01:53:49 · 752 阅读 · 0 评论 -
generative model and discriminative model
判别模型 和 生成模型 【摘要】 - 生成模型:无穷样本==》概率密度模型 = 产生模型==》预测 - 判别模型:有限样本==》判别函数 = 预测模型==》预测【简介】 简单的说,假设o是观察值,q是模型。 如果对P(o|q)建模,就是Generative模型。其基本思想是首先建立样本的概率密度模型,再利用模型进行推理预测。要求已知样本无穷或尽可能的大限制。 这种方法一般转载 2015-11-30 18:41:44 · 424 阅读 · 0 评论 -
Unsupervised Representation Learing with Deep Convolutional Generative Adversarial Networks
Recently, I am reading papers which is refer to Deep learning and Convolutional Networks(CNNs). The aim to write the blog is better understanding of above methods. Please forgive me there are full原创 2015-12-21 20:25:36 · 1053 阅读 · 0 评论 -
Unsupervised Rrpresentation Learning with Deep Convolutional Generative Adversarial Networks
Recently, I am reading some papers relating to unsupervised representation and convolutional network. The aim to write the blog is just to batter understand it. If there are misunderstandings or wrong原创 2015-12-21 19:33:01 · 844 阅读 · 0 评论