1. Trang chủ
  2. » Giáo án - Bài giảng

a dynamic neural field mechanism for self organization

2 1 0

Đang tải... (xem toàn văn)

THÔNG TIN TÀI LIỆU

Thông tin cơ bản

Định dạng
Số trang 2
Dung lượng 190,46 KB

Các công cụ chuyển đổi và chỉnh sửa cho tài liệu này

Nội dung

Bio Med CentralPage 1 of 2 page number not for citation purposes BMC Neuroscience Open Access Poster presentation A dynamic neural field mechanism for self-organization Lucian Alecu*1,2

Trang 1

Bio Med Central

Page 1 of 2

(page number not for citation purposes)

BMC Neuroscience

Open Access

Poster presentation

A dynamic neural field mechanism for self-organization

Lucian Alecu*1,2 and Hervé Frezza-Buet2

Address: 1 CORTEX, INRIA Nancy Grand-Est, 615 rue du Jardin Botanique, Villers-lès-Nancy, 54600, France and 2 IMS, SUPELEC Metz, 2 rue

Edouard Belin, Metz, 57070, France

Email: Lucian Alecu* - Lucian.Alecu@Supelec.fr; Hervé Frezza-Buet - Herve.Frezza-Buet@Supelec.fr

* Corresponding author

As introduced by Amari [1], dynamic neural fields (DNF)

are a mathematical formalism aiming to describe the

spa-tio-temporal evolution of the electrical potential of a

pop-ulation of cortical neurons Various cognitive tasks have

been successfully solved using this paradigm, but

never-theless, tasks requiring learning and self-organizing

abili-ties have rarely been addressed Aiming to extend the

applicative area of DNF, we are hereby interested in using

this computational model to implement such

self-organ-izing mechanisms Adapting the Kohonen's classical

algo-rithm [2] for developing self-organizing maps (SOM), we

propose a DNF-driven architecture that may deploy also a

self-organizing mechanism Benefiting from the

biologi-cally inspired features of the DNF, the advantage of such

structure is that the computation is fully-distributed

among its entities Unlike the classical SOM algorithm,

which requires a centralized computation of the global

maximum, our proposed architecture implements a

dis-tributed decision computation, based on the local

compe-tition mechanism deployed by neural fields Once the

architecture implemented, we investigate the capacity of

different neural field equations to solve simple

self-organ-ization tasks Our analysis concludes that the considered

equations (those of Amari [1] and Folias [3]) do not

per-form satisfactory, as seen in Figure 1, panels b and c

High-lighting the deficiencies of these equations that impeded

them to behave as expected, we propose a new system of

equations, enhancing that proposed by Folias [3] in order

to handle the observed undesired effects In summary, the

novelty of these equations consist in introducing an

adap-tive term that triggers the re-inhibition of a so-called

"unsustainable" bump of the field's activity (one that no longer is stimulated by strong input, but only but strong lateral excitation) As a conclusion, a field driven by the new equations achieves good results in solving the consid-ered self-organizing task (as seen in Figure 1d) Our research thus opens the way to new approaches that aim using dynamic neural field to solve more complex cogni-tive tasks

References

1. Amari S: Dynamics of pattern formation in lateral inhibition

type neural fields Biological Cybernetics 1977, 27:77-87.

2. Kohonen T: Self-Organization and Associative Memory, volume 8 of

Springer Series in Information Sciences Springer-Verlag; 1989

3. Folias SE, Bressloff PC: Breathers in two-dimensional neural

media Physical Review Letters 2005:95.

from Eighteenth Annual Computational Neuroscience Meeting: CNS*2009

Berlin, Germany 18–23 July 2009

Published: 13 July 2009

BMC Neuroscience 2009, 10(Suppl 1):P273 doi:10.1186/1471-2202-10-S1-P273

<supplement> <title> <p>Eighteenth Annual Computational Neuroscience Meeting: CNS*2009</p> </title> <editor>Don H Johnson</editor> <note>Meeting abstracts – A single PDF containing all abstracts in this Supplement is available <a href="http://www.biomedcentral.com/content/files/pdf/1471-2202-10-S1-full.pdf">here</a>.</note> <url>http://www.biomedcentral.com/content/pdf/1471-2202-10-S1-info.pdf</url> </supplement>

This abstract is available from: http://www.biomedcentral.com/1471-2202/10/S1/P273

© 2009 Alecu and Frezza-Buet; licensee BioMed Central Ltd

Trang 2

Publish with Bio Med Central and every scientist can read your work free of charge

"BioMed Central will be the most significant development for disseminating the results of biomedical researc h in our lifetime."

Sir Paul Nurse, Cancer Research UK Your research papers will be:

available free of charge to the entire biomedical community peer reviewed and published immediately upon acceptance cited in PubMed and archived on PubMed Central yours — you keep the copyright

Submit your manuscript here:

http://www.biomedcentral.com/info/publishing_adv.asp

BioMedcentral

BMC Neuroscience 2009, 10(Suppl 1):P273 http://www.biomedcentral.com/1471-2202/10/S1/P273

Page 2 of 2

(page number not for citation purposes)

Solving a one-dimensional self-organizing task, aiming to learn the herein shown coronal shape (inner radius 0.5, outer radius 1.0), with the support provided by the 3-layer architecture described in the document

Figure 1

Solving a one-dimensional self-organizing task, aiming to learn the herein shown coronal shape (inner radius 0.5, outer radius 1.0), with the support provided by the 3-layer architecture described in the document From

left to right: a Kohonen classical SOM; b Amari DNF; c Folias DNF; d the new DNF system of equations

Ngày đăng: 02/11/2022, 08:52