Communications of the ACM
A neural cocktail-party processor
Biological Cybernetics
A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
Unified theories of cognition
Redundant noisy attributes, attribute errors, and linear-threshold learning using winnow
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
Topics in parallel and distributed computation
Topics in parallel and distributed computation
Computational constraints on higher neural representations
Computational neuroscience
Qualitative reasoning: modeling and simulation with incomplete knowledge
Qualitative reasoning: modeling and simulation with incomplete knowledge
Circuits of the mind
Synchrony and desynchrony in integrate-and-fire oscillators
Neural Computation
A neuroidal architecture for cognitive computation
Journal of the ACM (JACM)
Java RMI: Remote Method Invocation
Java RMI: Remote Method Invocation
Connectionist inference models
Neural Networks
Java Language Specification, Second Edition: The Java Series
Java Language Specification, Second Edition: The Java Series
Design of High-Performance Microprocessor Circuits
Design of High-Performance Microprocessor Circuits
Semantic Networks: An Evidential Formalization and Its Connectionist Realization
Semantic Networks: An Evidential Formalization and Its Connectionist Realization
Biological grounding of recruitment learning and vicinal algorithms in long-term potentiation
Emergent neural computational architectures based on neuroscience
Spiking associative memory and scene segmentation by synchronization of cortical activity
Emergent neural computational architectures based on neuroscience
Types and Quantifiers in SHRUTI: A Connectionist Model of Rapid Reasoning and Relational Processing
Hybrid Neural Systems, revised papers from a workshop
Layered Hybrid Connectionist Models for Cognitive Science
Hybrid Neural Systems, revised papers from a workshop
Temporal binding as an inducer for connectionist recruitment learning over delayed lines
Neural Networks - 2003 Special issue: Advances in neural networks research IJCNN'03
A computational model of tractable reasoning: taking inspiration from cognition
IJCAI'93 Proceedings of the 13th international joint conference on Artifical intelligence - Volume 1
Hi-index | 0.01 |
The temporal correlation hypothesis proposes using distributed synchrony for the binding of different stimulus features. However, synchronized spikes must travel over cortical circuits that have varying-length pathways, leading to mismatched arrival times. This raises the question of how initial stimulus-dependent synchrony might be preserved at a destination binding site. Earlier, we proposed constraints on tolerance and segregation parameters for a phase-coding approach, within cortical circuits, to address this question [C. Gunay, A.S. Maida, Temporal binding as an inducer for connectionist recruitment learning over delayed lines, Neural Networks 16 (5-6) (2003) 593-600]. The purpose of the present paper is twofold. First, we conduct simulation studies that explore the effectiveness of the proposed constraints. Second, we place the studies in a broader context of synchrony-driven recruitment learning [L. Shastri, V. Ajjanagadde, From simple associations to systematic reasoning: a connectionist representation of rules, variables, and dynamic bindings using temporal synchrony, Behav. Brain Sci. 16 (3) (1993) 417-451; L.G. Valiant, Circuits of the Mind, Oxford University Press, Oxford, 1994] which brings together von der Malsburg's temporal binding [C. von der Malsburg, The correlation theory of brain function, in: E. Domany, J.L. van Hemmen, K. Schulten (Ed.), Models of Neural Networks, vol. 2, Physics of Neural Networks, Chapter 2, Springer, New York, 1994, pp. 95-120, (Originally appeared as a Technical Report at the Max-Planck Institute for Biophysical Chemistry, Gottingen, 1981)] and Feldman's recruitment learning [J.A. Feldman, Dynamic connections in neural networks, Biol. Cybern. 46 (1982) 27-39]. A network based on Valiant's neuroidal architecture is used to implement synchrony-driven recruitment learning. Complementing similar approaches, we use a continuous-time learning procedure allowing computation with spiking neurons. The viability of the proposed binding scheme is investigated by conducting simulation studies which examine binding errors. In the simulation, binding errors cause the formation of illusory conjunctions among features belonging to separate objects. Our results indicate that when tolerance and segregation parameters obey our proposed constraints, the sets of correct bindings are dominant over sets of spurious bindings in reasonable operating conditions. We also improve the stability of the recruitment method in deep hierarchies for use in limited size structures suitable for computer simulations. e also improve the stability of the recruitment method in deep hierarchies for use in limited size structures suitable for computer simulations.