French Doctoral Thesis available: neural information processing in retina
William Beaudot
beaudot at morgon.csemne.ch
Sun Feb 12 13:20:16 EST 1995
Hi,
Sorry, but this announce mainly concerns French readers.
-----------------------------------------------------------------------------
The following FRENCH Doctoral Thesis is available by FTP from the TIRFLab
ftp-server (Grenoble, France) and via WWW from my homepage.
FTP-host: tirf.inpg.fr
FTP-file: /pub/beaudot/MYTHESIS/*.ps.Z
WWW-link: ftp://tirf.inpg.fr/pub/HTML/beaudot/thesis.html
(8.6 Mo compressed, 30 Mo uncompressed, 249 pages,
splited into 11 compressed files,
one compressed postscript file per chapter)
-----------------------------------------------------------------------------
THE NEURAL INFORMATION PROCESSING IN THE VERTEBRATE RETINA:
A Melting Pot of Ideas for Artificial Vision
KEYWORDS : biological neural networks, retina
motion detection, directional selectivity
visual adaptation, signal processing
spatiotemporal processing, silicon retina
English Abstract:
The retina is the first neural structure involved in visual perception.
Researchers in Artificial Vision often see in it only a hard-wired circuit
scarcely more sophisticated than a video-camera, and dedicated to the
scanning of images and to the extraction of features leading to a simple
computation of Laplacian or temporal derivative.
In this thesis, we argue that it makes a lot of more, in particularly from
a dynamical point of view, aspect often neglected in Artificial Vision.
From a neurobiological inspiration, we show that the retina achieves a
spatiotemporal processing really suited to the regularization of visual data,
that it extracts a reliable and relevant spatiotemporal information, that it
performs a rough motion analysis composed of a motion detection and a
directional selectivity, and that it finally presents an elaborate mechanism
for the control of sensitivity.
This work emphasizes the fact once more that the solutions implemented by
nature are both simple and efficient (by a rather good trade-off between
complexity and performance), and that they should inspire the designers of
artificial visual systems. It also follows from this work two basic
consequences: a better understanding of the neural mechanisms involved in
early vision and a theoretical framework for the synthesis and analysis of
neuromorphic systems straight implementable into silicon.
French Abstract:
LE TRAITEMENT NEURONAL DE L'INFORMATION DANS LA RETINE DES VERTEBRES :
Un creuset d'idees pour la vision artificielle.
La retine est la toute premiere structure neuronale impliquee dans la
perception visuelle. Les chercheurs en Vision Artificielle n'y voient bien
souvent qu'un circuit cable a peine plus sophistique qu'une camera, dediee
a l'acquisition de l'image et a l'extraction de primitives se ramenant a un
simple calcul de laplacien et de derivee temporelle.
Dans cette these, nous soutenons qu'elle realise bien plus, en particulier
d' un point de vue dynamique, aspect encore souvent neglige en Vision Arti-
-ficielle. En nous appuyant sur des donnees neurobiologiques, nous montrons
qu'elle effectue un traitement spatio-temporel bien adapte a la regularisation
de l'information visuelle, qu'elle extrait une information spatio-temporelle
fiable et pertinente, qu'elle effectue une analyse rudimentaire du mouvement
composee d'une detection et d'une selectivite directionnelle, et enfin qu'elle
presente un mecanisme de controle de la sensibilite tout a fait remarquable.
Ce travail souligne encore une fois le fait que les solutions mises en
oeuvre par la nature sont a la fois simples et efficaces (par un bon compromis
entre la complexite et la performance), lesquelles devraient inspirer les
concepteurs de systemes en Vision Artificielle. De ce travail decoulent aussi
deux corollaires fondamentaux : une meilleure comprehension des mecanismes
neuronaux impliques dans la vision precoce et un cadre theorique pour la
synthese et l'analyse de systemes neuromorphiques directement implantables
sur silicium.
-----------------------------------------------------------------------------
FTP INSTRUCTIONS:
unix> ftp tirf.inpg.fr (or 192.70.29.33)
Name: anonymous
Password: <your e-mail address>
ftp> cd pub/beaudot/MYTHESIS
ftp> binary
ftp> mget *.ps.Z
ftp> quit
unix> uncompress *.ps.Z
Be careful : Compressed files require 8.6 Mo
-----------------------------------------------------------------------------
Feel free to contact me if you have any problem.
--
Dr. William H.A. BEAUDOT E-mail: beaudot at design.csemne.ch
C.S.E.M. IC & Systems Dept.: Bio-Inspired Advanced Research
Maladire 71, Case postale 41 Phone: (41) 38 205 251
CH-2007 Neuchtel (Switzerland) Fax: (41) 38 205 770
More information about the Connectionists
mailing list