machine learning rules!!!

http://tech.slashdot.org/story/09/07/03/0143233/IBM-Releases-Open-Source-Machine-Learning-Compiler

machine learning in future will be like computers today.

almost everywhere, there are computers.

now, computers are not just for computer scientists

who btw i don't think "scientists" though even i am a computer science student. :(

likewise, within decades, machine learning will be everywhere.

machine learning will rule :)

- H. Choi

superintelligence

http://www.forbes.com/2009/06/22/singularity-robots-computers-opinions-contributors-artificial-intelligence-09_land.html

http://www.forbes.com/2009/06/18/superintelligence-humanity-oxford-opinions-contributors-artificial-intelligence-09-bostrom.html

when computers get smarter than us in every thing, it seems to me the end of the world...

computers will get better (or at least same as the before) every single seconds...

and computers will never take a rest.... and they are supposed to be much faster than us...

so, once they get to have the human-level intelligence,

they will be able to prove every theories pretty soon and invent every possible machines...

so that there will be no more questions....

there is no more adventure... no more struggle, no more curiosity...

every stock market will be controlled by computers... every research will be done by computers...

computers will be much better entertainers, so that human entertainers will get fired...

basically, all the work will be done by computers... all the people will get fired...

all that we are going to do is just for fun...

but unfortuately, computers know better way how to make our pleasure...

so we will just sit and eat...and push a button for pleasure...

finally, we will be like pets to computers...

they will feed us with food and pleasure... and they do all the real fun stuff like adventure, research and enterainment...

even though they won't feel that way working on those stuff as we are not feeling fun when we work.

it means ending "the world" and starting a new world where there is no more fun... no more pain... just like a timeless space...

- H. Choi

statistical mechanics

"statistical mechanics can be viewed as a reconciliation of macroscopic thermodynamic laws with the reductionist approach of explaining macroscopic properties in terms of microscopic components."

- from wikipedia http://en.wikipedia.org/wiki/Reductionism

This is a nice explanation... :)

- H. Choi

history on manifold

history is on a manifold of space and time or we can say history is a manifold.
that's one of the reasons why we cannot understand the meaning of current
issues clearly. in that sense, the current time is on the edge of the manifold.
that's the reason why we have to look at the "past" to estimate (understand)
the meaning of "present."

still we cannot understand "present" perfectly until long time later when we can
see the issues on the manifold. then we will get to know the meanings more clearly.
unless we lose the facts, just it takes time .

- H. Choi

mirror neurons and motor theory

"Thus, to this point, whereas the exact nature of the link between speech production and perception remains to be discovered, existing evidence strongly indicates that perceptual systems have a much stronger influence on production than motor systems have on perception."

"We conclude that, rather than providing support for MT, mirror neurons are actually inconsistent with MT and are unlikely to have a central role in speech perception."

from A. J. Lotto, G. S. Hickok and L. L. Holt, "Reflections on mirror neurons and speech perception," Trends in Cognitive Sciences Vol.13 No.3, 2009. pp 110-114. 

so, how about other perception tasks rather than speech? 

still motor theory is attractive for perception at least to me, and mirror neuron theory seems like a bridge between motor theory and perception. 

- H. Choi

Uncertainty and Perception

Heisenberg Uncertainty Principle says when we observe something, our observation disturbs it. (It sounds weird.) 

Neuroscientists say the object exists only while we are observing it. (It is also weird.) 

So~ what do you say? :) 

Apr. 09, 2008

- H. Choi

being on a manifold.

Descartes said, 'I think, therefore I am.'

How can we reach to 'therefore I am' from 'I think'. 

To present data points, we need data space. Likewise, in order to reach the
conclusion 'therefore I am' we need to find the space for the existence.
Moreover, the 'being' should have any relationship with the space as in set theory. 

Thinking is not enough to be 'being' without any relationship with space
(or at least with other data points which makes the relationship with space.)

A data point is in a data space and the manifold gives more meaning to it. 

Descartes said, 'I think, therefore I am,' but God said, 'I am who I am.'

Dec. 03, 2006

- H. Choi

Florida! Yeah~

I am off to Florida tomorrow for two conference to present my papers as below.
(from Dec. 3 to Dec. 12)


Heeyoul Choi, Brandon Paulson and Tracy Hammond,
"Gesture Recognition based on Manifold Learning,"
in Proc. 12th International Workshop on Structural and Syntactic Pattern Recognition (SSPR-08),
Orlando, Florida, Dec. 4-6, 2008 (LNCS 5342 pp. 247-256).


Heeyoul Choi, Ricardo Gutierrez-Osuna, Seungjin Choi and Yoonsuck Choe,
"Kernel Oriented Discriminant Analysis for Speaker-Independent Phoneme Spaces,"
in Proc. 19th International Conference on Pattern Recognition (ICPR-08),
Tampa, Florida, Dec. 8-11, 2008.

Papers are available at my web page. 

Thank you, 

- H. Choi

"Thank you" mail.

...

Kernel isomap is a very powerful technique to visualize these nonlinear relations among variables. Thank you for letting us use your MatLab code all these years.

...

- Karl

I'm so glad and honored that somebody is enjoying my work...

Thank God.

- H. Choi

p.s.) All the codes as well as the papers are available at my web page http://people.cs.tamu.edu/hchoi/

Paper accepted :)

Thank God!
I got a paper accepted to SSPR 2008.
Thank you all.

Heeyoul Choi, Brandon Paulson and Tracy Hammond,
"Gesture Recognition based on Manifold Learning,"
LNCS, International Workshop on Structural and Syntactic Pattern Recognition (SSPR 2008),
Orlando,FL 2008 (Accepted)

- H. Choi

a response to my review...

Dear reviewer,

This is just to inform you that the author of the above manuscript, for which you have provided a review, has asked us to convey their thanks for your valuable comments.

It's my pleasure. :)

Actually I have reviewed journal papers since 2006, but I've never got this kind of response.
It's so kind of the author and I hope the paper gets published soon.. :)

- H. Choi

AAAI 08

AAAI 08 is almost over...we have one more day.... but it is a little disappointing...

First of all, the conference place is isolated from real Chicago... To get to the downtown, we have to take a bus and a train... it takes more than half an hour. Moreover, it is kind of dangerous around this place.
Second of all, the focus is different from my research interest... So i couldn't find any nice paper which I am interested in...
Third of all, the foods are not good... The snacks during coffee breaks are not good... and even reception foods look like just snacks.... not real food... (we had 3 reception... 2 of them were like just snacks). When it comes to food, IJCNN2004 in Budapest was perfect... I cannot forget it.
Last, but not least, there are not so many female students.... :(
One more thing, hotel does not have free internet... and everything is soooooo expensive here...

But the Chicago weather is fantastic... :) and I am having really good experiences...
Thank God... :)

- H. Choi

Lipschitz Global Optimization Algorithms

Dr. Sergeyev gave one interesting talk... check the below announcement.

Lipschitz constant can be used for function optimization. Curvature also can help...
According to Dr. Segeyev, his new method is much faster than DIRECT algorithm. But I don't buy it... because it seems like it depends on how the function looks...
Anyway, it was a really interesting seminar.

BTW, one other thing is he is not going to make his code publicly available... instead, he wants to sell it... :)
And, tomorrow morning, he is talking about a new computer machine which can handle infinite numbers, which sounds weirdly great. :)

-----------------------------------------------------------------------------------------
Industrial & Systems Engineering Seminar

Yaroslav Sergeyev
Distinguished Professor
Dipartimento di Elettronica
Informatica e Sistemistica Universita della Calabria, Italy

3:00 p.m., Wednesday July 10, 2008
Room 203, Zachry

TITLE: "Lipschitz Global Optimization Algorithms"

ABSTRACT
Global optimization problems with multidimensional objective functions satisfying the Lipschitz condition over a hyperinterval with an unknown Lipschitz constant are considered. It is supposed that the objective function can be "black box", multiextremal, and non-differentiable. It is also assumed that evaluation of the objective function at a point is a time-consuming operation. Different techniques based on various adaptive partition strategies are analyzed. The main attention is dedicated to diagonal algorithms, since they have a number of attractive theoretical properties and have proved to be efficient in solving applied problems. In these algorithms, the search hyperinterval is adaptively partitioned into smaller hyperintervals and the objective function is evaluated only at two vertices corresponding to the main diagonal of the generated hyperintervals. It is demonstrated that the traditional diagonal partition strategies do not fulfill the requirements of computational efficiency because of executing many redundant evaluations of the objective function. A new adaptive diagonal partition strategy that allows one to avoid such computational redundancy is described. Some powerful multidimensional global optimization algorithms based on the new strategy are introduced. Results of extensive numerical experiments performed to test the methods proposed demonstrate their advantages with respect to diagonal algorithms in terms of both number of trials of the objective function and qualitative analysis of the search domain, which is characterized by the number of generated hyperintervals.

- H. Choi

Chicago Travel, AAAI 08

I am going to Chicago for a week from this Saturday. AAAI 08.
I have two papers to be published... (both will be available on my homepage
right after the conference)


Heeyoul Choi, Seungjin Choi and Yoonsuck Choe,
"Manifold Integration with Markov Random Walks,"
 in Proc. 23rd Association for the Advanced of Artificial Intelligence (AAAI-08),
Chicago, Illinois, July 13-17, 2008.


Heeyoul Choi and Tracy Hammond,
"Sketch Recognition based on Manifold Learning,"
in Proc. 23rd Association for the Advanced of Artificial Intelligence (AAAI-08),
Chicago, Illinois, July 13-17, 2008.

Both are about manifold learning, though the first one is about integration
which is kind of a new concept and the second one is an application of
kernel Isomap to sketch data set.

Thank you,
- H. Choi

paper accepted :)

Thank God... I got a paper accepted to ICPR 08.

Heeyoul Choi, Ricardo Gutierrez-Osuna, Seungjin Choi and Yoonsuck Choe,
"Kernel Oriented Discriminant Analysis for Speaker-Independent Phoneme Spaces,"
in Proc. 19th International Conference on Pattern Recognition (ICPR-08),
Tampa, Florida, Dec. 8-11, 2008. (Accepted)

Thank you all,
- H. Choi

Brain-Computer Interface...

Recently, all the media all over the world are talking about World Science Festival on Wednesday, especially about brain-computer interface, which is so fascinating if we have.

http://www.forbes.com/technology/2008/05/29/mind-control-festival-tech-science-cx_ag_0529mind.html
According to this linked article above, basically the results are from invasive ways, which are relatively so easy...

Anyway, it is going to be amazing if we can control a computer or a car with just thinking. Someday, it will be...

- H. Choi

Q Gospel and Intelligent Design

It seems like Q Gospel and Intelligent Design (ID) are very similar.

Q Gospel says there might be some original source (Q gospel) which might have affected to other gospels so that the other gospels look similar, even sometimes some parts are same. On the other hand, ID says there might be some original source which might have affected to the whole universe so that a lot of phenomena or biological organs look similar, even sometimes some parts are same.

I know these are supported by totally different groups and there is no connection between these two discussions. But what I am saying here is the way how they are accepted by people. Q gospel is treated as a logical (or even scientific) argument and ID is treated as a religious faith (definitely not scientific) .

Of course, the level of the original sources are different. Q gospel is just one imaginary book and ID has one supernatural being as an original source. Here, I am just saying about the approach and the intention.

- H. Choi

Complex Cells and Object Recognition

S. Edelman, N. Intrator and T. Poggio, "Complex Cells and Object Recognition," NIPS97.

Note that this paper was published in 1997, which is 'long time ago.'
It says complex cells-like filter has invariant recognition. And, actually, it is really simple. Apply one filter for complex cells and check the correlation of the filter output to classify.

The problem is how to implement the complex cells-like filters. And we have one answer, which is independent subspace analysis (ISA) which is kind of a generalization of independent component analysis (ICA). BTW, ICA is a filter like simple cells.
The real problem is these theories are not like math theories. So the performance really depends on the situations such as noise or background or the shape of object.

Our brain is sooooo amazing... How does it do all these complicated stuffs?

- H. Choi

Active Control..

K. L. Harman, G. K. Humphrey, and M. A. Goodale, "Active Manual Control of Object Views Facilitates Visual Recognition," Current Biology, Vol. 9, No 22. pp1315-1318. 1999.

To sum up, first, observers who have active control on the object have better recognition than others who see the same sequence passively. The response time is shorter but accuracy is the same which is a little ackward. Second, active observers concentrate on certain angles than others. That is, this paper is kind of the first paper to emphasize on the active control.
But the reason why it is efficient is still a research topic to go.

In a word, active control is important on recognition, which now we all know and agree to... :)

- H. Choi

3D Geon Classification

W. Xing, W. Liu and B. Yuan, "A Novel Integrated Scheme for Extracting Superquadric-based Geons from 3D data," in Proc. of ICSP'04, 2004.

To my knowledge, this paper is the first paper to try to implement Geon Theory, even though this is just about Geon classification. They build up a superquadric-based model for 3D object data and optimize the parameters. And then they apply SVM to the extracted features from the parameters of the model to classify the object into geon classes.

This is not about 2D image but 3D data. And this makes a model for each 3D data and extract some features from the model parameters, which might be rotation and transition invariant. This does not sound natural and not a visual recognition.

- H. Choi