Self-organization in a perceptual network
- R. Linsker
- Computer ScienceComputer
- 1 March 1988
It is shown that even a single developing cell of a layered network exhibits a remarkable set of optimization properties that are closely related to issues in statistics, theoretical physics, adaptive signal processing, the formation of knowledge representation in artificial intelligence, and information theory.
From basic network principles to neural architecture: emergence of spatial-opponent cells.
- R. Linsker
- BiologyProceedings of the National Academy of Sciences…
- 1 October 1986
This paper is the first of three that address the origin and organization of feature-analyzing cells in simple systems governed by biologically plausible development rules, and introduces the theory of "modular self-adaptive networks," of which this system is an example, and explicitly demonstrates the emergence of a layer of spatial-opponent cells.
From basic network principles to neural architecture: emergence of orientation-selective cells.
- R. Linsker
- BiologyProceedings of the National Academy of Sciences…
- 1 November 1986
It is shown that orientation-selective cells, similar to the "simple" cortical cells of Hubel and Wiesel, emerge in a "modular self-adaptive network" containing several layers of cells with parallel feedforward connections whose strengths develop according to a Hebb-type correlation-rewarding rule.
Improving network robustness by edge modification
- A. Beygelzimer, G. Grinstein, R. Linsker, I. Rish
- Computer Science
- 15 November 2005
A measure of DNA periodicity.
- B. Silverman, R. Linsker
- Computer Science, BiologyJournal of Theoretical Biology
- 7 February 1986
From basic network principles to neural architecture: emergence of orientation columns.
- R. Linsker
- BiologyProceedings of the National Academy of Sciences…
- 1 November 1986
It is shown that, in the presence of lateral connections between developing orientation cells, these cells self-organize into banded patterns of cells of similar orientation, similar to the "orientation columns" found in mammalian visual cortex.
Perceptual neural organization: some approaches based on network models and information theory.
- R. Linsker
- Computer Science, MedicineAnnual Review of Neuroscience
- 1990
Article de synthese a propos de la modelisation de l'information et de l'expression des lois regissant les interactions entre les neurones sous formes d'algorithmes afin de comprendre l'organisation…
How to Generate Ordered Maps by Maximizing the Mutual Information between Input and Output Signals
- R. Linsker
- Computer ScienceNeural Computation
- 1 September 1989
A learning rule that performs gradient ascent in the average mutual information between input and an output signal is derived for a system having feedforward and lateral interactions and provides new links between unsupervised learning and information-theoretic optimization in a system whose properties are biologically motivated.
An Application of the Principle of Maximum Information Preservation to Linear Systems
- R. Linsker
- Computer ScienceNIPS
- 1988
This paper addresses the problem of determining the weights for a set of linear filters (model "cells") so as to maximize the ensemble-averaged information that the cells' output values jointly…
...
...