Recognition of partially occluded and rotated images with a network of spiking neurons
ABSTRACT In this paper, we introduce a novel system for recognition of partially occluded and rotated images. The system is based on a hierarchical network of integrate-and-fire spiking neurons with random synaptic connections and a novel organization process. The network generates integrated output sequences that are used for image classification. The proposed network is shown to provide satisfactory predictive performance given that the number of the recognition neurons and synaptic connections are adjusted to the size of the input image. Comparison of synaptic plasticity activity rule (SAPR) and spike timing dependant plasticity rules, which are used to learn connections between the spiking neurons, indicates that the former gives better results and thus the SAPR rule is used. Test results show that the proposed network performs better than a recognition system based on support vector machines.
- SourceAvailable from: Muhammad Aqil
[Show abstract] [Hide abstract]
- "Dynamic behavior of neuron is widely studied to explore the chief role of neuronal spiking for effective neurotransmission and brain signal processing     . External electrical stimulation (EES), like deep brain stimulation, is a therapy for cognitive disorders such as Parkinson's disease, epilepsy and dystonia . "
ABSTRACT: This paper discusses the synchronization of three coupled chaotic FitzHugh–Nagumo (FHN) neurons with different gap junctions under external electrical stimulation. A nonlinear control law that guarantees the asymptotic synchronization of coupled neurons (with reduced computations) is proposed. The developed control law incorporates the synchronization error between two slave neurons in addition to the conventionally considered synchronization errors between the master and the slave neurons, which make the proposed scheme computationally more efficient. Further, a novel L2 gain reduction criterion has been developed for multi-input multi-output systems with non-zero initial conditions, and is applied to robust synchronization of FHN neurons under L2 norm bounded disturbance and uncertainties. Furthermore, a robust adaptive nonlinear control law is developed, which is capable of handling variations in nonlinear part of synchronization error dynamics, without using any neural-network-based training-oriented adaptive scheme. The proposed control schemes ensure global synchronization with computational simplicity, easy way of design and implementation and avoiding extra measurements. The results obtained with the proposed control laws are verified through numerical simulations.Neurocomputing 10/2011; 74(17):3296-3304. DOI:10.1016/j.neucom.2011.05.015 · 2.08 Impact Factor
- "Other mathematical models of biologically inspired neurons are optimized for real time response of the neural network ,  and  or for biological plausibility such as Izhikevich models  and . A simple but biologically plausible rule for modeling the synaptic mechanisms of learning (SAPR) is presented in  and . More complex models of neurons which mimic rigorously the synaptic chemical and physical processes were developed and simulated by Henry Markram et. "
Conference Paper: Power dissipation of CMOS ASICs[Show abstract] [Hide abstract]
ABSTRACT: High levels of power dissipation in CMOS ASICs are a result of high speed and complexity which exacerbates numerous design issues due to elevated junction temperatures. A method of calculating total power dissipation, as viewed from the gate level in an ASIC design methodology is presented and the effects of power dissipation are examined. Techniques for reducing power dissipation are described and other design and analysis issues are consideredASIC Conference and Exhibit, 1991. Proceedings., Fourth Annual IEEE International; 10/1991