文章分类 - 深度学习（转载）
1
摘要：【角度】一文教你如何确定好的“学习率” 本文转载自：专知，来源：专知内容组（编） 【导读】近日，数据科学家Hafidz Zulkifli发布一篇文章，主要讲解了深度学习中的“学习率”，以及如何利用学习率来提高深度学习模型的性能并减少训练时间。作者从“学习率”入手，逐层抽丝剥茧教我们深入理解深度学习中
阅读全文
摘要：Learning rate这件小事 1. Learning Rate Finder Deep learning models are typically trained by a stochastic gradient descent optimizer. There are many variat
阅读全文
摘要：不同loss函数在不同网络结构下的误差后传 前言 推导下最小均方差（MSE）和交叉熵（CE）两种loss函数的导数，看看还是否满足误差后传的原则？有什么区别？ 在一般地网络结构下是怎么样的？在CNN下又是怎么推导的？在RNN结构下（LSTM）又是怎么推导的？直接讨论多元判别的情况，二元读者自行推导。
阅读全文
摘要：Transposed Convolution, Fractionally Strided Convolution or Deconvolution 反卷积（Deconvolution）的概念第一次出现是Zeiler在2010年发表的论文Deconvolutional networks中，但是并没有指
阅读全文
摘要：Lessons learned from manually classifying CIFAR-10 CIFAR-10 Note, this post is from 2011 and slightly outdated in some places. Statistics. CIFAR-10 co
阅读全文
摘要：Preliminary Note on the Complexity of a Neural Network This post is a preliminary note on the “complexity” of neural networks. It’s a topic that has n
阅读全文
摘要：Where does the Sigmoid in Logistic Regression come from? « A Note on the Graph Laplacian « A Note on the Graph Laplacian Where does the Sigmoid in Log
阅读全文
摘要：Deep Learning in Neural Networks: An Overview Deep Learning in Neural Networks: An Overview – Schmidhuber 2014 What a wonderful treasure trove this pa
阅读全文
摘要：How can I know if Deep Learning works better for a specific problem than SVM or random forest? If we tackle a supervised learning problem, my advice i
阅读全文
摘要：机器学习(Machine Learning)&深度学习(Deep Learning)资料(Chapter 2) 《Image Scaling using Deep Convolutional Neural Networks》 介绍:使用卷积神经网络的图像缩放. 《Proceedings of The
阅读全文
摘要：机器学习(Machine Learning)&深度学习(Deep Learning)资料(Chapter 1) 《Brief History of Machine Learning》 介绍:这是一篇介绍机器学习历史的文章，介绍很全面，从感知机、神经网络、决策树、SVM、Adaboost到随机森林、D
阅读全文
摘要：Compilation of Useful Deep Learning Resources Note : This list is incomplete and open for updates. If you know some useful resource which has not been
阅读全文
摘要：Understanding Convolution in Deep LearningPosted ByTim Dettmerson Mar 26, 2015 |61 commentsConvolution is probably the most important concept in deep ...
阅读全文
摘要：Top 10 Deep Learning Tips & TricksDeep Learning has been at the forefront of data science innovations throughout 2015. Dr. Arno Candel offers help thr...
阅读全文
摘要：Deep Learning’s AccuracyDeep learning has knocked down one record after another on benchmark dataset after benchmark dataset since 2006. In many compe...
阅读全文
1
浙公网安备 33010602011771号