Yang Li

A hung Parliament explained- By Professor Robert Hazell, UCL

 Uncategorized  No Responses »
May 082010
 

A hung Parliament explained- By Professor Robert Hazell, UCL

Wiki: hung parliament: 悬吊国会/无多数议会

In parliamentary systems, a hung parliament is one in which no political party has an outright majority of seats. In nations in which single member districts are used to elect parliament, and there are weak regional parties, such as the United Kingdom, a hung parliament is a rarity, as in these circumstances one party will usually hold enough seats to form a majority. A hung parliament will usually force either a coalition government, a minority government or a dissolution of parliament. Frequent hung parliaments can result in smaller parties staying in power for decades as they switch support between the two or three major parties.

No more @Googlemail in UK!! Gmail returns!

 google  No Responses »
May 052010
 

Google was forced to give its e-mail service Gmail a different name, Googlemail, because of a trademark dispute in the UK. These disputes take a long time.  This @googlemail address has been annoying me for ages…Finally…

According to Google:

“As of May 3, 2010, Google’s email service is changing its name to Gmail in the United Kingdom. From now on, anybody who signs up for a new Gmail account in the UK will get an @gmail.com address instead of @googlemail.com. The good news is that “gmail” is 50% fewer characters than “googlemail,” and with so much emailing going on these days, we estimate this name change will save something like 60 million keystrokes a day. At approximately 217 microjoules per keystroke, that’s about the energy of 20 bonbons saved every day!If you already use Google Mail and would prefer an @gmail.com address, you have the option to change to the matching @gmail.com username. If you make this address swap, it only affects your address; your account settings, contacts, and existing mail won’t change, and any mail sent to your old @googlemail.com address will automatically redirect to your new address. ”

http://mail.google.com/mail/googlemail/rebrand

For some reason, the link is not working. I hope they can fix this asap so I can switch back to GMAIL!

Eager Learning VS Lazy Learning

 Machine Learning  No Responses »
May 032010
 

Eager Learning:

Eager learning methods construct a general and explicit description of target function based on the provided training examples.

Eager learning methods use the same approximation to the target function, which must be learned based on training examples and before input queries are observed

Lazy Learning

Lazy learning methods simply store the data and generalizing beyond these data is postponed until an explicit request is made.

Lazy learning methods can construct a different approximation to the target function for each encountered query instance.

Suitable for complex and incomplete problem domains, where a complex target function can be represented by a collection of less complex local approximations.

Eager Learning normally requires less space than Lazy Learning does

Decision Tree Learning Algorithm and ID3

 Machine Learning  No Responses »
May 032010
 

General Decision Tree learning algorithms:

Employ top-down greedy search through the space of possible solutions.

1, Perform a statistical test of each attribute to determine how well it classifies the training examples when considered alone

2.Select the attributes that perform the best and use it as the root of the tree.

3. To decide the descendant node down each branch of the root, sort the training examples according to value related to the current branch and repeat the process in steps 1 and 2.

ID3:

ID3 uses Information Gain to determine how informative an attribute.

Information Gain is based on a measure that we call Entropy: which characterizes the impurity of a collection of examples S.  (The larger the Entropy, the larger the impurity)

Advantage:

1. Every discrete classification function can be represented by a decision tree.

2. Instead of making decisions based on individual training examples( e.g. Find-S), ID3 uses statistical property of all the examples(Information Gain), therefore less sensitive to errors (compare to Find-S, Candidate-Elimination).

Disadvantages:

1. ID3 determines a single hypothesis, not a space of consistent hypotheses.

2. No back tracking in its search, therefore ID3 may overfit the training data and converge to local optimal solution that is not globally optimal.

How to stop Overfitting?

1. Stop the training process before the learner reaches the point where it perfectly classifies the training data.

2. Apply backtracking – post pruning of overfitted tree

3. Cross Validation

Difference between Find-S and Candidate-Elimination Algorithms

 Machine Learning  No Responses »
May 032010
 

Find-S :

Find-S is guaranteed to output the most specific hypothesis h that best fits positive training examples.

The hypothesis h returned by Find-S will also fit negative examples as long as training examples are correct.

Candidate-Elimination:

Outputs a description of set of all hypotheses consistent with the training examples.

General commands for Visual Editor(vi)

 linux/unix  No Responses »
Apr 252010
 

What is vi?

The default editor that comes with the UNIX operating system is called vi (visual editor). [Alternate editors for UNIX environments include pico andemacs, a product of GNU.]

* vi filename edit filename starting at line 1
vi -r filename recover filename that was being edited when system crashed

Note: The cursor moves to bottom of screen whenever a colon (:) is typed. This type of command is completed by hitting the <Return> (or <Enter>) key.

Continue reading »

iPhone OS 4 vs. Windows Phone 7

 Mobile Phones  No Responses »
Apr 092010
 

Eye-catching feature from iPhone:

Multitasking: Some consider it the biggest weaknesses of the iPhone in comparison with its smartphone peers: that Apple limits the ability of applications on the iPhone or iPod Touch to run simultaneously. Currently, you can do some multitasking–listening to music while reading e-mail, or browsing Safari during a voice call–but third-party applications can’t do this at all.

On the contrary, Microsoft reported early that they decided to emulate Apple and eliminate multitasking support in its upcoming Windows Mobile 7 operating system.


Some comparisons:

Continue reading »

 Newer Entries