A neural cocktail-party processor
Biological Cybernetics
Image segmentation based on oscillatory correlation
Neural Computation
Weakly connected neural networks
Weakly connected neural networks
The handbook of brain theory and neural networks
Phase equations for relaxation oscillators
SIAM Journal on Applied Mathematics
Pattern recognition via synchronization in phase-locked loop neural networks
IEEE Transactions on Neural Networks
Locally excitatory globally inhibitory oscillator networks
IEEE Transactions on Neural Networks
Temporal coding: Assembly formation through constructive interference
Neural Computation
Assemblies as Phase-Locked Pattern Sets That Collectively Win the Competition for Coherence
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Temporal coding: competition for coherence and new perspectives on assembly formation
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
| Hi-index | 0.00 |
Using an oscillatory network model that combines classical network models with phase dynamics, we demonstrate how the superposition catastrophe of pattern recognition may be avoided in the context of phase models. The model is designed to meet two requirements: on and off states should correspond, respectively, to high and low phase velocities, and patterns should be retrieved in coherent mode. Nonoverlapping patterns can be simultaneously active with mutually different phases. For overlapping patterns, competition can be used to reduce coherence to a subset of patterns. The model thereby solves the superposition problem.