Pattern recognition using pulse-coupled neural networks and discrete Fourier transforms

Mureșan, Raul C.

doi:10.1016/s0925-2312(02)00727-0

Cited by 69 publications

(33 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In principle, considering a target neuron and a pool of inhibitory interneurons, each time an afferent spike arrives, the inhibitory pool shunts down the efficacy of spike integration of the target neuron by the means of shunting inhibition. Simple implementations of such a neural coding proved their power in dealing with large amounts of information [4,18,19,21]. The enormous encoding power of this scheme has been outlined by S.J.…”

Section: Neural Mechanismsmentioning

confidence: 97%

Scale Independence in the Visual System

Mureșan¹

2004

Neural Information Processing: Research and Development

View full text Add to dashboard Cite

Abstract. We briefly present some aspects of information processing in the mammalian visual system. The chapter focuses on the problem of scaleindependent object recognition. We provide a simple model, based on spiking neurons that make use of shunting inhibition in order to optimally select their driving afferent inputs. The model is able to resist to some degree to scale changes of the stimulus. We discuss possible mechanisms that the brain could use to achieve invariant object recognition and correlate our model with biophysical evidence.

show abstract

Section: Neural Mechanismsmentioning

confidence: 97%

Scale Independence in the Visual System

Mureșan¹

2004

Neural Information Processing: Research and Development

View full text Add to dashboard Cite

show abstract

“…The time signature is widely applied in the related fields of pattern recognition [63][64][65][66][67][68][69][70][71][72][73]. Rughooputh et al use an improved PCNN (called by pulse-coupled-multilayer perceptron hybrid neural network) to monitor Condition [63] and apply this network into forensic application [64].…”

Section: Time Signaturementioning

confidence: 99%

Review of pulse-coupled neural networks

Wang

Cheng

et al. 2010

Image and Vision Computing

230

View full text Add to dashboard Cite

“…Separate populations of neurons encode either synchrony or asynchrony in the stimulus pattern. Synchrony builds up ultra-rapidly, by the means of lateral interaction [6]. Predominantly, lateral interaction is inhibitory, the receptive field (RF) profile resembling with a center-surround structure (narrow center excitation and wide, silent surround suppression).…”

Section: General Architecturementioning

confidence: 99%