Biology-Inspired Early Vision System for a Spike Processing Neurocomputer
نویسندگان
چکیده
Examinations of the early vision system of mammals have shown Gabor-like behaviour of the simple cell responses. Furthermore, the advantages of Gabor-like image ltering are evident in computer vision. This causes strong demand to achieve Gabor-like responses in biology inspired spiking neural networks and so we propose a neural vision network based on spiking neurons with Gabor-like simple cell responses. The Gabor behaviour is theoretically derived and demonstrated with simulation results. Our network consists of a cascaded structure of photoreceptors, ganglion and horizontal neurons and simple cells. The receptors are arranged on a hexagonal grid. One main advantage of our approach compared to direct Gabor ltering is the availability of valuable intersignals. The network is designed as the preprocessing stage for pulse-coupled neural vision networks simulated on the SPIKE neurocom-puter architecture. Hence, the simple cells are implemented as Eckhorn neurons.
منابع مشابه
Towards Efficient Hardware for Spike-processing Neural Networks
We present the requirements for a neurocomputer for spike-processing neural networks. In a simulation study we investigated the performance of available hardware and showed, that there is still a need for a specific neurocomputer dedicated to the simulation of spike-processing networks. On the basis of our simulation study and an investigation of the features of spike-processing networks we ana...
متن کاملHebbian On-line Learning for Spike-processing Neural Networks
We present a Hebbian learning rule for spike-processing neural networks. Spike-processing networks are mainly used for figure-ground segregation and object recognition. They have been introduced according to experimental results and theoretical studies which suggest that temporal correlation of activity might be used by the brain as a code for feature binding and figure-ground segregation. The ...
متن کاملNeuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE
In this paper we present a complete spike-based architecture: from a Dynamic Vision Sensor (retina) to a stereo head robotic platform. The aim of this research is to reproduce intended movements performed by humans taking into account as many features as possible from the biological point of view. This paper fills the gap between current spike silicon sensors and robotic actuators by applying a...
متن کاملA Hybrid Radial Basis Function Neurocomputer and Its Applications
A neurocomputer was implemented using radial basis functions and a combination of analog and digital VLSI circuits. The hybrid system uses custom analog circuits for the input layer and a digital signal processing board for the hidden and output layers. The system combines the advantages of both analog and digital circuits. featuring low power consumption while minimizing overall system error. ...
متن کاملUniversal Learning Neurocomputers ∗
A universal learning neurocomputer is a brain– inspired information processing system that can be taught to perform, in principle, an arbitrary algorithm (universal in Turing’s sense). Conventional computers and universal Turing machines are examples of universal programmable systems. However, the process of programming these systems does not match our intuitive notion of teaching and learning ...
متن کامل