Paul Erdos...

the followings are copied from http://en.wikipedia.org/wiki/Paul_Erdős

Other idiosyncratic elements of Erdős' vocabulary include:

• children were referred to as "epsilons";
• women were "bosses";
• men were "slaves";
• people who stopped doing math had "died";
• people who physically died had "left";
• alcoholic drinks were "poison";
• music was "noise";
• people who had married were "captured";
• people who had divorced were "liberated";
• to give a mathematical lecture was "to preach" and
• to give an oral exam to a student was "to torture" him/her.

Animation about Searle's Chinese Room Argument

http://www.mind.ilstu.edu/curriculum/searle_chinese_room/searle_chinese_room.php

one nice animation is way much better than 100 pages' text... ^^

R.I.P. Sam Roweis

http://www.huffingtonpost.com/2010/01/14/sam-roweis-nyu-professor-_n_421500.html

What a tragic loss to us all in machine learning including manifold learning.

Rest In Peace... Dr. Roweis....

Bees can recognize faces?

http://www.nytimes.com/2010/02/02/science/02bees.html?emc=tnt&tntemail1=y

They say bees can recognize human faces... Can you believe it? :)

I am not sure about it, but as Dr. Forsyth said, we definitely have to have animal studies

on face recognition research. That's for sure.

- H. Choi

HMAX

M. Riesenhuber and T. Poggio,

"Hierarchical Models of Object Recognition in Cortex,"

Nature Neurosciece, Vol. 2, No. 11, November 1999. pp 1019-1025.

They say simple cells and complex cells and

complex cells are responsible for invariant properties.

Invariance can be implemented as a pooling mechanism

where there are view-invariant units and view-tuned units.

Hierarchical feedforward network is considered and

the network is based on MAX rather than linear summation (SUM).

MAX is proved to be more robust and invariant than SUM.

That is, Hierarchical MAX has view-invariant object recognition ability

and is supported by biological (physiological) facts.

Anyway, I say, this is a very similar concept to ISA, but a little more flexible.

But this paper doesn't say much of implementation such as

how to get the simple cells or complex cells,

and how to construct the network structure.

See [1] for a specific implementation and examples of HMAX.

In [1], interestingly, simple and complex cells are not learned from data

but designed by second derivative of Gaussians.

[1] T. Serre and M. Riesenhuber,

"Realistic Modeling of Simple and Complex Cell Tuning in the HMAX Model,

and Implications for Invariant Object Recognition in Cortex,"

AI Memo 2004-017, CBCL Memo 239, MIT, July 2004.

- H. Choi

"models of object recognition"

M. Riesenhuber and T. Poggio,

"Models of Object Recognition,"

Nature Neurosciece Supplement, Vol. 3, November 2000. pp 1199-1204

It's a review paper about object recognition models.

Here is what I got from the paper.

"the distinction between identification and categorization is mostly semantic."

There are two kinds of models for object recognition.

1. view-based model: "objects are represented as collections of view- specific features"

It is something like ICA.

2. object-centered model: there is 3-D model of the object.

It's something like Geon theory.

They took "view-based model" in this paper.

Considering the speed of processing in the brain,

feedback model cannot be the prime model for object recognition.

It should be more like feedforward processing

where invariant properties can be obtained by hierarchical structure.

Making the connections between input image to higher level units as in Fig. 3,

the different tasks (categorization and identification) can be achieved by learning.

- H. Choi

Defense!!!

DISSERTATION DEFENSE OF

HEEYOUL "HENRY" CHOI

TITLE: Manifold Integration: Data Integration on Multiple Manifolds

Advisor: Dr. Yoonsuck Choe

2:00 p.m. Room 307 HRBB

- H. Choi

two papers accepted!!!

Thank God! Finally!

Thank the coauthors!

- Heeyoul Choi, Seungjin Choi, Anup Katake and Yoonsuck Choe,

"Learning Alpha-Integration with Partially-Labeled Data,"

in Proc. IEEE Int. Conf. Acousitcs, Speech and Signal Processing (ICASSP),

Dallas, Texas, March 15-19, 2010.

- Heeyoul Choi, Anup Katake, Seungjin Choi and Yoonsuck Choe,

"Alpha-Integration of Multiple Evidence,"

in Proc. IEEE Int. Conf. Acousitcs, Speech and Signal Processing (ICASSP),

Dallas, Texas, March 15-19, 2010.

- H. Choi

"Boom! Hok! A Monkey Language Is Deciphered"

http://www.nytimes.com/2009/12/08/science/08monkey.html?emc=tnt&tntemail1=y

Monkey is actually speaking!!! ???

interesting...

one more interesting point would be,

we analyze all the video/audio input and speak a lot about the understanding,

while other animals can analyze a lot of input but speaking not so much about it...

is it because their understanding is worse than ours? or just syntax is not enough?

or their memory system is worse?

think about "a dog never barks about yesterdays' burglar." (it might be not so true though)

- H. Choi

tensor analysis

"General relativity is formulated completely in the language of tensors.

Einstein had learned about them, with great difficulty, from the geometer

Marcel Grossmann. Levi-Civita then initiated a correspondence with Einstein

to correct mistakes Einstein had made in his use of tensor analysis."

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

Einstein had learned about tensors "WITH GREAT DIFFICULTY."

And Levi-Civita wanted to correct Einstein's misunderstanding.

Hm... interesting... :)

- H. Choi

paper accepted...

I got a paper accepted to ICONIP2009 as follows... FINALLY... it's like million years ago
when we wrote it ...

Heeyoul Choi, Anup Katake, Seungjin Choi, Yoonseop Kang and Yoonsuck Choe,

"Probabilistic Combination of Multiple Evidence,"

in Proc. 16th Int. Conf. on Neural Information Processing (ICONIP),

Bangkok, Thailand, December 1-5, 2009. (to appear in LNCS)

Thank you all... and thank God...

- H. Choi

Statistics also rules!

yeap!

http://www.nytimes.com/2009/08/06/technology/06stats.html?hp

- H. Choi

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