我經常在 TopLanguage 討論群組上推薦一些書籍,也經常問裡面的牛人們搜羅一些有關的資料,人工智慧、機器學習、自然語言處理、知識發現(特別地,資料採礦)、資訊檢索 這些無疑是 CS 領域最好玩的分支了(也是互相緊密聯絡的),這裡將最近有關機器學習和人工智慧相關的一些學習資源歸一個類: 首先是兩個非常棒的 Wikipedia 條目,我也算是 wikipedia 的重度使用者了,學習一門東西的時候常常發現是始於 wikipedia 中間經過若干次 google ,然後止於某一本或幾本著作。
Reviewers give a score of between 1 and 10 for each paper. The program committee will interpret the numerical score in the following way: 10: Top 5% of accepted NIPS papers, a seminal paper for the ages. I will consider not reviewing for NIPS again
zz from http://news.mydrivers.com/1/138/138813.htmIBM近日發布一款開源智能編譯器Milepost GCC(GNU Compiler Collection),並宣稱這也是全球首款開源的智能編譯器,它可以自動學習如何最佳化嵌入式程式並大幅縮短軟體開發時間,所有使用者都可到Milepost官方網站下載Milepost GCC。 根據IBM的初步測試,IBM System P伺服器上運行Milepost
How to do research? Find a research point. Read new paper,such as ICCV,CVPR,PAMI.If you find some new idea,which can be made use of in your work,you can do it. Think it before you do it,analyze why you do it like that. If you have a problem,talk
總是聽到這兩個術語,但是又一直不清楚它們最本質的區別。今天花了一小點時間來徹底的弄清楚了。得到的結論如下:Discriminative Model是判別模型,又可以稱為條件模型,或條件機率模型。Generative Model是產生模型,又叫產生式模型。二者的本質區別是discriminative model 估計的是條件機率分布(conditional distribution)p(class|context)generative model 估計的是聯合機率分布(joint
Simultaneous dimension reduction and regression or supervised dimension reduction (SDR) MethodsOutline:29 July 2009 KAI MAO, QIANG WU,FENG LIANG,SAYAN MUKHERJEE. Two models for Bayesian supervised dimension reduction. Presenter: Xinwei Jiang,