随笔分类 -  调参（转载）

1 2 3 下一页
Neural Network Hyperparameters
摘要：Neural Network HyperparametersMost machine learning algorithms involve “hyperparameters” which are variables set before actually optimizing the model'... 阅读全文
posted @ 2015-12-23 19:34 菜鸡一枚 阅读(597) 评论(0) 推荐(0) 编辑
11 Clever Methods of Overfitting and how to avoid them
摘要：11 Clever Methods of Overfitting and how to avoid themOverfitting is the bane of Data Science in the age of Big Data. John Langford reviews "clever" m... 阅读全文
posted @ 2015-12-22 19:20 菜鸡一枚 阅读(324) 评论(0) 推荐(0) 编辑
Deep Learning in a Nutshell: History and Training
摘要：Deep Learning in a Nutshell: History and TrainingThis series of blog posts aims to provide an intuitive and gentle introduction to deep learning that ... 阅读全文
posted @ 2015-12-18 19:19 菜鸡一枚 阅读(346) 评论(0) 推荐(0) 编辑
FITTING A MODEL VIA CLOSED-FORM EQUATIONS VS. GRADIENT DESCENT VS STOCHASTIC GRADIENT DESCENT VS MINI-BATCH LEARNING. WHAT IS THE DIFFERENCE?
摘要：FITTING A MODEL VIA CLOSED-FORM EQUATIONS VS. GRADIENT DESCENT VS STOCHASTIC GRADIENT DESCENT VS MINI-BATCH LEARNING. WHAT IS THE DIFFERENCE?In order ... 阅读全文
posted @ 2015-12-14 19:39 菜鸡一枚 阅读(519) 评论(0) 推荐(0) 编辑
How much training data do you need?
摘要：How much training data do you need?//@樵夫上校: 0. 经验上，10X规则（训练数据是模型参数量的10倍）适用与大多数模型，包括shallow network. 1.线性模型可以应用10X的经验规则，模型参数是特征选择后的数量（PCA等方法）。2.NN可以将10... 阅读全文
posted @ 2015-11-29 20:53 菜鸡一枚 阅读(487) 评论(0) 推荐(0) 编辑
Recruit Coupon Purchase Winner's Interview: 2nd place, Halla Yang
摘要：Recruit Coupon Purchase Winner's Interview: 2nd place, Halla YangRecruitPonpareis Japan's leading joint coupon site, offering huge discounts on everyt... 阅读全文
posted @ 2015-10-22 19:33 菜鸡一枚 阅读(307) 评论(0) 推荐(0) 编辑
CIKM Competition数据挖掘竞赛夺冠算法陈运文
摘要：CIKM Competition数据挖掘竞赛夺冠算法陈运文背景CIKM Cup(或者称为CIKM Competition)是ACM CIKM举办的国际数据挖掘竞赛的名称。CIKM全称是International Conference on Information and Knowledge Mana... 阅读全文
posted @ 2015-10-16 19:23 菜鸡一枚 阅读(2153) 评论(0) 推荐(0) 编辑
Training (deep) Neural Networks Part: 1
摘要：Training (deep) Neural Networks Part: 1Nowadays training deep learning models have become extremely easy with high-quality libraries such as Torch and... 阅读全文
posted @ 2015-10-14 19:25 菜鸡一枚 阅读(613) 评论(0) 推荐(0) 编辑
Liberty Mutual Property Inspection, Winner's Interview: Qingchen Wang
摘要：Liberty Mutual Property Inspection, Winner's Interview: Qingchen WangThe hugely popular Liberty Mutual Group: Property Inspection Predictioncompetitio... 阅读全文
posted @ 2015-09-29 19:39 菜鸡一枚 阅读(551) 评论(0) 推荐(0) 编辑
ICDM Winner's Interview: 3rd place, Roberto Diaz
摘要：ICDM Winner's Interview: 3rd place, Roberto DiazThis summer, theICDM 2015conferencesponsoredacompetitionfocusedon makingindividual user connections ac... 阅读全文
posted @ 2015-09-17 18:58 菜鸡一枚 阅读(214) 评论(0) 推荐(0) 编辑
Diabetic Retinopathy Winner's Interview: 1st place, Ben Graham
摘要：Diabetic Retinopathy Winner's Interview: 1st place, Ben GrahamBen Graham finished at the top of the leaderboard in the high-profileDiabetic Retinopath... 阅读全文
posted @ 2015-09-11 19:06 菜鸡一枚 阅读(415) 评论(0) 推荐(0) 编辑
Training Neural Networks: Q&A with Ian Goodfellow, Google
摘要：Training Neural Networks: Q&A with Ian Goodfellow, GoogleNeural networks require considerable time and computational firepower to train. Previously, r... 阅读全文
posted @ 2015-09-05 18:34 菜鸡一枚 阅读(232) 评论(0) 推荐(0) 编辑
Machine Learning Trick of the Day (2): Gaussian Integral Trick
摘要：Machine Learning Trick of theDay (2): Gaussian Integral TrickToday's trick, theGaussian integral trick, is one that allows us to re-expressa (potentia... 阅读全文
posted @ 2015-09-04 19:53 菜鸡一枚 阅读(420) 评论(0) 推荐(0) 编辑
Machine Learning Trick of the Day (1): Replica Trick
摘要：Machine Learning Trick of theDay (1): Replica Trick'Tricks' of all sorts are used throughoutmachine learning, in both research and in production setti... 阅读全文
posted @ 2015-09-04 19:28 菜鸡一枚 阅读(518) 评论(0) 推荐(0) 编辑
Bayesian optimisation for smart hyperparameter search
摘要：Bayesian optimisation for smart hyperparameter searchFitting a single classifier does not take long, fitting hundreds takes a while. To find the best ... 阅读全文
posted @ 2015-08-15 19:06 菜鸡一枚 阅读(419) 评论(0) 推荐(0) 编辑
CIFAR-10 Competition Winners: Interviews with Dr. Ben Graham, Phil Culliton, & Zygmunt Zając
摘要：CIFAR-10 Competition Winners: Interviews with Dr. Ben Graham, Phil Culliton, & Zygmunt ZającDr. Ben GrahamDr. Ben Grahamis an Assistant Professor in S... 阅读全文
posted @ 2015-08-10 17:34 菜鸡一枚 阅读(609) 评论(0) 推荐(0) 编辑
Deep Learning: Assuming a deep neural network is properly regulated, can adding more layers actually make the performance degrade?
摘要：Deep Learning:Assuming a deep neural network is properly regulated, can adding more layers actually make the performance degrade?I found this to be re... 阅读全文
posted @ 2015-08-04 19:55 菜鸡一枚 阅读(298) 评论(0) 推荐(0) 编辑
Cross Validation done wrong
摘要：Cross Validation done wrongCross validation is an essential tool in statistical learning1to estimate the accuracy of your algorithm. Despite its great... 阅读全文
posted @ 2015-07-30 19:32 菜鸡一枚 阅读(448) 评论(0) 推荐(0) 编辑
CrowdFlower Winner's Interview: 1st place, Chenglong Chen
摘要：CrowdFlower Winner's Interview: 1st place, Chenglong ChenTheCrowdflower Search Results Relevancecompetition asked Kagglers toevaluate the accuracy of ... 阅读全文
posted @ 2015-07-29 20:02 菜鸡一枚 阅读(928) 评论(0) 推荐(0) 编辑
Taxi Trip Time Winners' Interview: 3rd place, BlueTaxi
摘要：Taxi Trip Time Winners' Interview: 3rd place, BlueTaxiThis spring, Kaggle hostedtwo competitions with theECML PKDD conferencein Porto, Portugal. The c... 阅读全文
posted @ 2015-07-26 19:01 菜鸡一枚 阅读(508) 评论(0) 推荐(0) 编辑

1 2 3 下一页