papers, books, resources

记录一下网上看到的paper：

1.Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition(微软语音识别DNN)

2.Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Network(Google的街景门牌号识别,DistBelief,深度卷积神经网络)

3.Quantitative Information Flow as Network Flow Capacity(Stephen2008,扭曲图像恢复)

4.Draft：Deep Learning in Neural Networks：An Overview(Juergen Schmidhuber)

5.Improving neural networks by preventing co-adaptation of feature detectors(Hinton2012,dropout training)

6.Learning Features from Music Audio with Deep Belief Networks

7.Simple-Demographics-Often-Identify-People-Uniquely(只要知道年龄、性别和邮编，并与公开的数据库交叉对比，便可识别出87%的人的身份)

8.A tutorial survey of architectures,algorithms,and applications for deep learning(Li Deng)

 

OCR relevant:

1.Robust Text Detection in Natural Scene Images

2.Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification(Juergen Schmidhuber,中文手写识别)

3.Transfer Learning for Latin and Chinese Characters with Deep Neural Networks

4.Reading Digits in Natural Images with Unsupervised Feature Learning(http://cvisioncentral.com/projects/?project=314)

 

Books:

1.机器学习实战

2.Computer Vision ： Models, Learning, and Inference

3.Character Recognition Systems ： A Guide for Students and Practitioners(2007,Cheriet)

4.DEEP LEARNING：METHODS AND APPLICATIONS(Li Deng,有语音识别,Information Retrieval,以及Computer Vision方面的应用)

5.planning algorithm

"作者Steven M. LaValle伊大教授: http://msl.cs.uiuc.edu/~lavalle/ 本书以多种格式提供,主题涵盖机器人,控制理论,人工智能,计算机图像学,特别主题包括运动规划"(http://weibo.com/1715118170/Az6qEi48G?type=repost#!/1715118170/Az6qEi48G?type=comment)

6.算法引论：一种创造性方法

7.统计学习方法(李航)

8.统计学习基础 数据挖掘、推理与预测

9.The LION Way: Machine Learning plus Intelligent Optimization

"短短300多页道尽机器学习的方方面面. 图文并茂, 生动易懂, 没有一坨坨公式的烦恼. 适合新手入门打基础, 也适合老手温故而知新. 比起MLAPP/PRML等大部头, 也许这本你更需要."(http://weibo.com/1847310855/B3G8W2A5N)

http://1.oito.eu/The-LION-Way-Machine-Learning-plus-Intelligent-Optimization.pdf

10.Theory of Convex Optimization for Machine Learning

http://www.princeton.edu/~sbubeck/Bubeck14.pdf

"普林斯顿大学Bubeck教授关于优化的新书《机器学习凸优化理论》,整体感觉是短小精悍，材料很新，适合对理论有兴趣的同学参考。"(http://weibo.com/1657470871/B5jcIsyZ4?type=repost)

11.Algorithms(2006,Sanjoy Dasgupta, Christos Papadimitriou, Umesh Vazirani).

书评：http://book.douban.com/review/1325850/

 

websites:

1.A Large set of Machine Learning Resources for Beginners to Mavens

http://www.erogol.com/large-set-machine-learning-resources-beginners-mavens/

 2.machine learning open source software

http://mloss.org/software/

 3.Best Paper Awards in Computer Science (since 1996)

http://jeffhuang.com/best_paper_awards.html

4.Machine Learning Surveys(A list of literature surveys, reviews, and tutorials on Machine Learning and related topics)

http://www.mlsurveys.com/

5.Computer Vision Projects

http://cvisioncentral.com/projects/

6.ASU的优化工具集,包括C/C++, Matlab, Java的constrained, unconstrained optimization, least squares, linear programming, integer linear programming等等

http://plato.asu.edu/sub/pns.html

 7.Scikit-Learn：开源的机器学习Python模块

http://code.csdn.net/news/2819741

 8.一个Python学习网站，分享较多机器学习的Python实现代码：

http://nbviewer.ipython.org/github/rasbt/

 9.Spark好用的机器学习库：

(1)MLlib(Machine Learnig lib)：可用于二元分类、线性回归、逻辑回归、聚类、协同过滤等。

http://spark.apache.org/mllib/

(2)Liblinear: 大神林智仁近期发布的Spark LIBLINEAR，可用于分类、LR、SVM、SVR(Support Vector Regression)等。

http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/distributed-liblinear/spark/running_spark_liblinear.html