qygroup.blogspot.com

bcao.wordpress.com

March | 2008 | Thinking in Learning

https://bcao.wordpress.com/2008/03

124; Comments RSS. An Interesting Discussion in Our Group. Posted on March 7, 2008. Things start from my email which sent to our group mail list on an interesting passage as following. Don’t delete this just because it looks weird. Believe it or not, you can read it. Then people in our group began to post interesting comments on this passage. Continue reading →. 124; Leave a comment. Review for Gaussian Distribution. Posted on March 6, 2008. Gaussain distribution for univariate random variable.

bcao.wordpress.com

Order Statistic | Thinking in Learning

https://bcao.wordpress.com/2008/04/28/order-statistic

124; Comments RSS. Posted on April 28, 2008. Consider the following problem:. Given k bottles and 1 liter of water, we randomly split the water into these bottles. Let. Be the volume of water in. Bottle, what is the distribution of. The problem can be model by the following process. We random generated k-1 real numbers. In [0,1] with uniform distribution. Then the interval [0,1] is split into k intervals. We can regard length of. Interval as the random variable. Be iid. Let. In this case,. You are commen...

bcao.wordpress.com

Notes in Implementing RVM | Thinking in Learning

https://bcao.wordpress.com/2008/04/27/notes-in-implementing-rvm

124; Comments RSS. Notes in Implementing RVM. Posted on April 27, 2008. Due to the sparse property of RVM, many of the. Would approach infinity. This would cause the Hessian matrix to be singular and the inverse operation to be ill-posed. Therefore, we take the method in (Nabney,1999) to avoid such a problem. By multiplying both side with. Is the solution of. Is the solution of equation. Hence we convert the inverse operation into solving linear equations which is more stable. Leave a Reply Cancel reply.

bcao.wordpress.com

April | 2007 | Thinking in Learning

https://bcao.wordpress.com/2007/04

124; Comments RSS. Posted on April 2, 2007. To do list today:. Test multi-instance method on SVM;. Error analysis on AI experiment;. Run KNN experiment on Fraud Detection;. Error Correct Coding method for AI experiment. Function path = viterbi path(prior, transmat, obslike). VITERBI Find the most-probable (Viterbi) path through the HMM state trellis. Path = viterbi(prior, transmat, obslik)% Inputs:% prior(i) = Pr(Q(1) = i). Transmat(i,j) = Pr(Q(t 1)=j Q(t)=i). Obslik(i,t) = Pr(y(t) Q(t)=i). Scaled = 1;.

bcao.wordpress.com

An Interesting Discussion in Our Group | Thinking in Learning

https://bcao.wordpress.com/2008/03/07/an-interesting-discussion-in-our-group

124; Comments RSS. An Interesting Discussion in Our Group. Posted on March 7, 2008. Things start from my email which sent to our group mail list on an interesting passage as following. Don’t delete this just because it looks weird. Believe it or not, you can read it. Then people in our group began to post interesting comments on this passage. 8212; Prof. Yang:. Tjsmld yp nom gpt drmfomh yjr omyrtrdyomh go;r yp id/ o yjoml oy od trs; u gim yp trsf oy/ ;ryd drr ejsy er vsm fp om trdrstvj! B How long is the...

bcao.wordpress.com

March | 2007 | Thinking in Learning

https://bcao.wordpress.com/2007/03

124; Comments RSS. Posted on March 20, 2007. 今天在用perl的正则表达式的时候，发现怎么用也用不对，就连最简单的 $string = /substr/ 都不对。 Bin labels(find( orig labels(:,i)= 1) = 1;. Bin labels(find( orig labels(:,i) =1) = 2;. Function new label = labelconverter(old label). Fid = fopen(old label, ‘rt’);. While feof(fid) = 0. Tline = fgetl(fid);. Labels = str2num(tline);. Num = length(labels);. Vlabel = [y, labels(i),1];. S = [s;vlabel];. New label = full(sparse(s(:,1),s(:,2),s(:,3) );. Save old label’.new’ new label;. For i=1:num data,.

bcao.wordpress.com

June | 2007 | Thinking in Learning

https://bcao.wordpress.com/2007/06

124; Comments RSS. Posted on June 29, 2007. Netflix is so interesting! But it is not easy to get a little improvment. It is a good chance to learn something from trying to solve it. 124; Leave a comment. Home Page @ HKUST. Natural language processing blog. Blog at WordPress.com. Blog at WordPress.com. Follow “Thinking in Learning”. Get every new post delivered to your Inbox. Build a website with WordPress.com.

bcao.wordpress.com

Tips | Thinking in Learning

https://bcao.wordpress.com/perl-tips

124; Comments RSS. My $key (sort { $a = $b } (keys(%hash) ) {. Change the width of cmd window: open cmd.exe under system32, right click the top and select properties. You can change the font as well as the size of the window. Leave a Reply Cancel reply. Enter your comment here. Fill in your details below or click an icon to log in:. Address never made public). You are commenting using your WordPress.com account. ( Log Out. You are commenting using your Twitter account. ( Log Out. Home Page @ HKUST.

bcao.wordpress.com

July | 2007 | Thinking in Learning

https://bcao.wordpress.com/2007/07

124; Comments RSS. Posted on July 17, 2007. Hal Daume III gave an excellent tutorial on Bayesian Techniques for NLP at MSRA. Although the tutorial’s name is about NLP but actually it is all about graphical models. In this tutorial, Hal showed many detail usually you cannot read directly from the papers. He also gave us some vivid illusion of abstract ideas such as Metropolis-Hastings Sampling and Gibbs Sampling etc. Why the accept probability in Metropolis-hastings Sampling is:. 124; 1 Comment. Indicates...

bcao.wordpress.com

Reading Lists | Thinking in Learning

https://bcao.wordpress.com/reading-lists

124; Comments RSS. A Scalable Kernel-Based Algorithm for Semi-Supervised Metric Learning. Diffusion Kernels on Statistical Manifolds. Graphical Models, Exponential Families, and Variational Inference. Dynamics of large networks. Learning with Matrix Factorizations. Pattern Recognition and Machine Learning. Probabilistic Reasoning in Intelligent Systems. Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond. Correcting Sample Selection Bias by Unlabeled Data.