connectome...

now in nyt, connectome is getting more attention... :)
http://www.nytimes.com/2010/12/28/science/28brain.html

in addition to the questions stated in the article, i got some more... 

1. structure at one point to functions? 

2. embodiment? each brain is connected to its own body... so probably we might

have to slice all the body... otherwise, the difference from different brain structure 

may be from different sensory input or different environment... 

3. overfitting? each brain has too many millions neurons and we can have "some" data 

(like a few data points in a very high dimensional space)...

In Search of Memory

"In Search of Memory" by Eric R. Kandel, winner of the Nobel prize.

a well written summary of neuroscience... with focus on memory.
and his life experience and wisdom.

i should have read this book earlier...
then it could have changed my research and even my life.

this is a must read to engineering or science students...

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

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

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