【知识图谱——机器大脑中的知识库】 最近写了一篇关于知识图谱的科普短文《知识图谱——机器大脑中的知识库》,未来可能会成为一本书中的一章,先放出来敬请大家指正:O网页链接
【课程资料: (Caltech)John Preskill的量子计算】《Physics 219/Computer Science 219 - Quantum Computation》John PreskillO网页链接
【DNN特征表示用于无监督学习的用例】《Unsupervised Learning: Use Cases》O网页链接
【论文:微博时序迁移熵分析】《The dynamic of information-driven coordination phenomena: a transfer entropy analysis》J Borge-Holthoefer, N Perra, B Gonçalves, S González-Bailón, A Arenas (2015)O网页链接
《爱可可老师今日视野(15.07.26)》( 分享自@简书)O网页链接
【论文:分布式矩阵补全与(鲁棒)分解】《Distributed Matrix Completion and Robust Factorization》L. Mackey, A. Talwalkar, M. I. Jordan (JMLR2015)O网页链接DFC&Code:O网页链接
【论文:面向大规模机器学习的自动模型搜索TUPAQ】《Automating Model Search for Large Scale Machine Learning》E. Sparks, A. Talwalkar, D. Haas, M. Franklin, M. I. Jordan, T. Kraska (SOCC2015) pdf:O网页链接 arXiv上的版本《TuPAQ: An Efficient Planner for Large-scale Predictive Analytic Queries》O网页链接
【论文:基于sketching实现快速可靠的张量分解】《Fast and Guaranteed Tensor Decomposition via Sketching》Y Wang, H Tung, A Smola, A Anandkumar (2015)O网页链接
【Python/Pandas/Matplotlib/Scikit-learn通过自行车数据分析西雅图工作习惯】《Learning Seattle's Work Habits from Bicycle Counts (Updated!)》O网页链接
【开源:基于Torch的RNN文本生成】"Playground for some RNN stuff in Torch" GitHub:O网页链接
#state-of-the-art#新书【Convex Optimization AlgorithmsO网页链接O网页链接】 MIT课程【Convex Analysis and OptimizationO网页链接】
《MPI 简易入门》O网页链接
#Mirror Descent#The Mirror Descent AlgorithmO网页链接Mirror descent and nonlinear projected subgradient methods, 2003O网页链接Tutorial: Mirror Descent Algorithms for Large-Scale Deterministic and Stochastic Convex Optimization, 2012O网页链接
COLT的open problem: The landscape of the loss surfaces of multilayer networks AISTAT的问题结论:The Loss Surfaces of Multilayer Networks 传送门:COLTO网页链接AISTATO网页链接
arXiv [1507.06411] Arbitrariness of peer review: A Bayesian analysis of the NIPS experiment,从贝叶斯分析NIPS,看同行评审的意义O网页链接
“RNN以及LSTM的介绍和公式梳理” RNN-LSTM 今年太火了 最近刷Image Caption 要刷榜基本靠它了最近看了不少RNN的,记录一下~~~~~《RNN以及LSTM的介绍和公式梳理》 - DarkScope从这里开始 - 博客频道 - CSDN.NETO网页链接
模拟似乎成了统计论文的必须套路,但是如果留心,还是有论文不做模拟的,比如:Antoniak (1974). Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems. The annals of statistics, 1152-1174.O网页链接--还有哪些著名的论文是没有simulation的? 这个链接不要钱:O网页链接
我在北大的CIPS暑期学校信息抽取讲座主要讲了三部分:基本的命名实体抽取方法和实践、关系抽取一些较新的进展、以及最新推断和抽取的联合模型。 幻灯片已经放到CMU主页上,可以下载了:O网页链接
Lifelong Machine Learning in the Big Data Era - Tutorial at IJCAI 2015, Zhiyuan Chen and Bing Liu.O网页链接
Facebook natural image generation using ConvNets, code:O网页链接
Introducing Jupyter Notebooks in Azure ML Studio:O网页链接
New transcription for Google Voice: using LSTM, cut the transcription errors by 49%...O网页链接
【A new look at the system, algorithm, and theory foundations of scalable machine learning】T29: A new look at the system, algorithm, and theory foundations of scalable machine learning. - Eric P. Xing and Qirong Ho, ijcai-15 tutorial.O网页链接
看好概率图模型PGM的未来:1)目前深度学习效果好,靠的大量标注样本。要利用好无标注样本学特征,个人觉得用PGM建生成模型最靠谱。2)PGM现在也融入深度学习,来拟合几个概率分布函数,缓解PGM学习和推断的困难,具体参考DeepMind和Kingma&Welling的文章。人想登月不能靠爬树,得造火箭,虽然很艰难。
Python for Image Understanding: Deep Learning with Convolutional Neural NetsO网页链接
Easy Bayesian Bootstrap in R:O网页链接