摘要: Facebook IV Winner's Interview: 1st place, Peter Best (aka fakeplastictrees)Peter Best (akafakeplastictrees) took 1st place inHuman or Robot?,our four... 阅读全文
posted @ 2015-06-27 19:39 菜鸡一枚 阅读(379) 评论(0) 推荐(0) 编辑
摘要: An Attempt to Understand Boosting Algorithm(s)WELCOME!Here you will find dailynews and tutorials about R, contributed by over 573 bloggers.There are m... 阅读全文
posted @ 2015-06-27 19:20 菜鸡一枚 阅读(370) 评论(0) 推荐(0) 编辑
摘要: A Statistical View of DeepLearning (V): Generalisation and RegularisationWe now routinely buildcomplex, highly-parameterised models in an effort to ad... 阅读全文
posted @ 2015-06-27 19:18 菜鸡一枚 阅读(306) 评论(0) 推荐(0) 编辑
摘要: A Statistical View of Deep Learning(IV): Recurrent Nets and Dynamical SystemsRecurrent neural networks (RNNs) are now established as one of the key to... 阅读全文
posted @ 2015-06-27 19:14 菜鸡一枚 阅读(359) 评论(0) 推荐(0) 编辑
摘要: 阅读全文
posted @ 2015-06-27 19:10 菜鸡一枚 阅读(150) 评论(0) 推荐(0) 编辑
摘要: 阅读全文
posted @ 2015-06-27 19:09 菜鸡一枚 阅读(359) 评论(0) 推荐(1) 编辑
摘要: A Statistical View of DeepLearning (III): Memory and KernelsMemory,the ways in which we remember and recall past experiences and data to reason about ... 阅读全文
posted @ 2015-06-27 19:08 菜鸡一枚 阅读(245) 评论(0) 推荐(0) 编辑
摘要: Can deep learning help you find the perfect girl?One of the first things I did when I moved to Montreal was installingTinder. For those of you not fam... 阅读全文
posted @ 2015-06-27 19:05 菜鸡一枚 阅读(281) 评论(0) 推荐(0) 编辑
摘要: 阅读全文
posted @ 2015-06-27 19:03 菜鸡一枚 阅读(251) 评论(0) 推荐(0) 编辑
摘要: A Statistical View of Deep Learning(II): Auto-encoders and Free EnergyWith the success ofdiscriminative modellingusing deep feedforward neural network... 阅读全文
posted @ 2015-06-27 19:01 菜鸡一枚 阅读(517) 评论(0) 推荐(0) 编辑
摘要: Kaggle Bike Sharing Demand Prediction – How I got in top 5 percentile of participants?IntroductionThere are three types of peoplewhotake part in aKagg... 阅读全文
posted @ 2015-06-27 19:00 菜鸡一枚 阅读(801) 评论(0) 推荐(0) 编辑
摘要: A Statistical View of DeepLearning (I): Recursive GLMsDeep learningand the use of deep neural networks [1] are now established as a key tool for pract... 阅读全文
posted @ 2015-06-27 18:58 菜鸡一枚 阅读(349) 评论(0) 推荐(0) 编辑
摘要: Why GEMM is at the heart of deeplearningI spend most of my time worrying about how to make deep learning with neural networks faster and more power ef... 阅读全文
posted @ 2015-06-27 18:55 菜鸡一枚 阅读(1076) 评论(0) 推荐(0) 编辑
摘要: [CV]人脸识别检测数据集做了一段时间的人脸识别和检测,在这里列一下用过的数据集。基本上,大家近期也都是在这几个数据集上检测自己的算法。网上这方面的总结虽然不少,但是一则有些是多年前的数据,或是规模太小或是链接已经失效,再则是数据集的测试协议定义不明,不尽适合用来和其它方法做比较。1.Labeled... 阅读全文
posted @ 2015-06-27 18:51 菜鸡一枚 阅读(6765) 评论(0) 推荐(0) 编辑
摘要: 视频图像去模糊常用处理方法随着“平安城市”的广泛建设,各大城市已经建有大量的视频监控系统,虽然监控系统己经广泛地存在于银行、商场、车站和交通路口等公共场所,但是在公安工作中,由于设备或者其他条件的限制,案情发生后的图像回放都存在图像不清晰,数据不完整的问题,无法为案件的及时侦破提供有效线索。经常出现... 阅读全文
posted @ 2015-06-27 18:48 菜鸡一枚 阅读(6619) 评论(0) 推荐(1) 编辑
摘要: Computational Methods in Bayesian AnalysisComputational Methods in Bayesian Analysis【Markov chain Monte Carlo】【Gibbs Sampling】【The Metropolis-Hastings... 阅读全文
posted @ 2015-06-27 18:45 菜鸡一枚 阅读(484) 评论(0) 推荐(0) 编辑
摘要: 阅读全文
posted @ 2015-06-27 18:37 菜鸡一枚 阅读(131) 评论(0) 推荐(0) 编辑
摘要: 阅读全文
posted @ 2015-06-27 18:35 菜鸡一枚 阅读(201) 评论(0) 推荐(0) 编辑