Neural blackboard architectures: the realization of compositionality and systematicity in neural networks

Journal of Neural Engineering
M de Kamps, F van Der Velde

Abstract

In this paper, we will first introduce the notions of systematicity and combinatorial productivity and we will argue that these notions are essential for human cognition and probably for every agent that needs to be able to deal with novel, unexpected situations in a complex environment. Agents that use compositional representations are faced with the so-called binding problem and the question of how to create neural network architectures that can deal with it is essential for understanding higher level cognition. Moreover, an architecture that can solve this problem is likely to scale better with problem size than other neural network architectures. Then, we will discuss object-based attention. The influence of spatial attention is well known, but there is solid evidence for object-based attention as well. We will discuss experiments that demonstrate object-based attention and will discuss a model that can explain the data of these experiments very well. The model strongly suggests that this mode of attention provides a neural basis for parallel search. Next, we will show a model for binding in visual cortex. This model is based on a so-called neural blackboard architecture, where higher cortical areas act as processors, speci...Continue Reading

References

Mar 1, 1988·Cognition·J A Fodor, Z W Pylyshyn
Jan 1, 1972·Biophysical Journal·H R Wilson, J D Cowan
Jan 1, 1980·Cognitive Psychology·A M Treisman, G Gelade
Jan 1, 1995·Annual Review of Neuroscience·W Singer, C M Gray
May 27, 1993·Nature·L ChelazziR Desimone
Apr 1, 1996·Journal of Veterinary Pharmacology and Therapeutics·D K MugeA Livingston
Feb 14, 1998·Nature·J P GottliebM E Goldberg
Aug 5, 1998·Cognition·S Pinker
Jan 1, 1995·Physical Review. E, Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics·W Gerstner
Jul 17, 1999·Rapid Communications in Mass Spectrometry : RCM·C McConvilleD Flood
Mar 16, 2001·Journal of Experimental Psychology. Human Perception and Performance·E K VogelS J Luck
Jun 5, 2001·Journal of Cognitive Neuroscience·F van Der Velde, M de Kamps
Sep 21, 2001·Journal of Cognitive Neuroscience·A Raffone, G Wolters
Oct 23, 2001·Neural Networks : the Official Journal of the International Neural Network Society·M de Kamps, F van der Velde
Nov 21, 2001·Nature Reviews. Neuroscience·J Duncan
May 24, 2003·Consciousness and Cognition·Richard J Tunney, David R Shanks
Jun 23, 2005·Neural Computation·Bruno A Olshausen, David J Field
Mar 18, 2006·The Behavioral and Brain Sciences·Georg F Striedter

❮ Previous
Next ❯

Citations


❮ Previous
Next ❯

Related Concepts

Related Feeds

Brain-Computer Interface

A brain-computer interface, also known as a brain-machine interface, is a bi-directional communication pathway between an external device and a wired brain. Here is the latest research on this topic.

Related Papers

The Behavioral and Brain Sciences
F van Der Velde, M de Kamps
Journal of Physiology, Paris
Edmund T Rolls, Simon M Stringer
Computers in Biology and Medicine
S K Chittajallu, D Wong
Journal of Vision
Drazen Domijan, Mia Setić
© 2021 Meta ULC. All rights reserved