This paper presents a circuit design technique suitable for the realization of winner-take-all (WTA), maximum (MAX), looser-take-all (LTA), and minimum (MIN) circuits. The technique presented is based on current replication and comparison. Traditional techniques rely on the matching of an N transistors array, where N is the number of system inputs. This implies that when N increases, as the siz...

The use of competitive activation units in deep convolutional neural networks (ConvNets) is generally understood as a way of building one network by the combination of multiple sub-networks, with each one being capable of solving a simpler task when compared to the complexity of the original problem involving the whole dataset [1]. Similar ideas have been explored in the past using multi-layer ...

The principles by which spiking neurons contribute to the astounding computational power of generic cortical microcircuits, and how spike-timing-dependent plasticity (STDP) of synaptic weights could generate and maintain this computational function, are unknown. We show here that STDP, in conjunction with a stochastic soft winner-take-all (WTA) circuit, induces spiking neurons to generate throu...

We present a parallel analog vector quantizer (VQ) in 2.0m double-poly CMOS technology and analyze its energetic efficiency. The prototype chip contains an array of 16 16 charge-based distance estimation cells, implementing a 16 analog input, 4-b coded output VQ with a mean absolute difference (MAD) distance metric. The distance cell including dynamic template storage measures 60 78 m. The outp...

We introduce two dynamical optimization coupling mechanisms for getting different kinds of synchronization in adaptive complex networks. At each node in the network there is an oscillator and the ensemble of oscillators could be either identical or non-identical. For each oscillator, we adjust only one incoming link’s strength in different time intervals while the other incoming links’ strength...

An adaptive high precision image object centroid center of mass (COM) detection system employing a 2-D dynamic element matching (DEM) algorithm for object tracking is presented. This proposed system outputs a high resolution COM location of the most salient object in the field of view for tracking and navigation purposes and is suitable for real time applications. Precomputation object detectio...

In Piekniewski & Schreiber (2008) we have developed a simple mathematical model for information flow structure in a class of recurrent neural networks and shown that its asymptotic behaviour is scale-free and admits a description in terms of the so-called winner-take-all dynamics. In the present paper we establish a limit theorem for spectra of the spike-flow graphs induced by the winner-take-a...

In this paper, we derive classifiers which are winner-take-all (WTA) approximations to a Bayes classifier with Gaussian mixtures for class conditional densities. The derived classifiers include clustering based algorithms like LVQ and k-Means. We propose a constrained rank Gaussian mixtures model and derive a WTA algorithm for it. Our experiments with two speech classification tasks indicate th...

Delayed-response tasks (DRTs) have been used to assess working memory (WM) processes in human and non-human animals. Experiments have shown that the basal ganglia (BG) and dorsolateral prefrontal cortex (DLPFC) subserve DRT performance. Here, we report the results of simulation studies of a systems-level model of DRT performance. The model was trained using the temporal difference (TD) algorith...

Studies of collective human behaviour in the social sciences, often grounded in details of actions by individuals, have much to offer ‘social' models from the physical sciences concerning elegant statistical regularities. Drawing on behavioural studies of social influence, we present a parsimonious, stochastic model, which generates an entire family of real-world right-skew socio-economic distr...