Time complexity:

Average:O(n2)
Best case: O(n)
Worst case: O(n2)

Pseudo code

Continue reading →

Popularity: 1% [?]

Algorithm outline:
——————–
(from video)

1. Start with neural network (single or multiple layer).
2. Present the training sample, compute the activation values of all the units until we compute the activation values of output layer units.
3. Compare the output that we computed with the training sample output to compute the error.
4. Having computed the error, our objective is to re-adjust the weight so the error decreases so that our computed values is closer to the real values.
5. Done with one training sample, we’ll continue with the next training sample.
6. Use learning rate to choose slow or fast learning. Slow learning is better in general, because of gradient descent.
7. Continue with this learning until ideally we reach state where the weight doesn’t change too much.
8. Freeze the weight, and we have learn the function.

Backpropagation

1. Compute the error of the output layers, and then aproportion that error to the hidden layers.
2. Having the error of the hidden layer, use two layer learning algorithms to readjust the weights (weight adjustment formula). Multi-layer neural networks work better than single layer. Continue reading →

Popularity: 2% [?]

Design Pattern Websites:

Go4Expert Forum
http://www.go4expert.com/forums/showthread.php?t=5127

SourceMaking
http://sourcemaking.com/design_patterns

OODesign
http://www.oodesign.com/

Wikipedia
http://en.wikipedia.org/wiki/Software_design_pattern#Classification_and_list

Design Pattern Books:

Popularity: 2% [?]

Course term: Spring 2012
Website: Official course website.
Course Professor: Prof. Ken Backlawski
Textbook: Object-Oriented Software Engineering Using UML, Patterns, and Java (3rd Edition)

Continue reading →

Popularity: 2% [?]

Some of my friends are curious about what actually I learn on the Master of Computer Science program I’m taking now.

And although sometimes I post about some of the course lessons and notes on my blog, I think it’s a good idea if I write a central page that organized these posts and categorized them to the courses I took. These will also serve as notes both while I’m in the program, and someday when I completed the program.

The following are courses that I took, and I’m specializing in Database management, for a complete list of courses that the program offers, check the Northeastern MSCS program website. Continue reading →

Popularity: 2% [?]

Course term: Spring 2012 – Northeastern University
Website: course official website.
Course Professor:Professor Mirek Riedewald
Textbook: Data Mining: Concepts and Techniques, Third Edition (The Morgan Kaufmann Series in Data Management Systems)

Some of the outline item will have a separate detailed post.
Continue reading →

Popularity: 3% [?]

We all love good and commented codes, but most of us either don’t know how to write a good comment for our codes, or just plain lazy to write one.

In Java, JavaDoc is pretty much the industry standard when it comes to auto-generated code tool. And as a strong believer of good software development practice, I always put comments on my code.

To save time, I created this template for methods so I can always refresh myself about how to write a good JavaDoc for my code. These codes are taken from the Java SDK source codes, so talk about how the creator of the Java write their comments (no one can be more expert than them I suppose). Continue reading →

Popularity: 4% [?]

Think of starting Scrum Agile Development in your team? but you’re not so sure where to start? read the Scrum Primer!
Continue reading →

Popularity: 6% [?]

My notes of XML schema from Methods of Software Development course (CS6520) in Northeastern University. Continue reading →

Popularity: 12% [?]

This is just going to be a very short notes about difference between the getDeclaredAnnotations and getAnnotations method of Java java.lang.Class<T> class.

I was googling for the answer but didn’t immediately got any article that explains it, so I thought why I not create it myself.

So what is the difference: Continue reading →

Popularity: 10% [?]