Spiking neural networks (SNN) have gained popularity in embedded applications such as robotics and computer vision. The main advantages of SNN are the temporal plasticity, ease of use in neural interface circuits and reduced computation complexity. SNN have been successfully used for image classification. They provide a model for the mammalian visual cortex, image segmentation and pattern recognition. Different spiking neuron mathematical models exist, but their computational complexity makes them ill-suited for hardware implementation. In this paper, a novel, simplified and computationally efficient model of spike response model (SRM) neuron with spike-time dependent plasticity (STDP) learning is presented. Frequency spike coding based on receptive fields is used for data representation; images are encoded by the network and processed in a similar manner as the primary layers in visual cortex. The network output can be used as a primary feature extractor for further refined recognition or as a simple object classifier. Results show that the model can successfully learn and classify black and white images with added noise or partially obscured samples with up to ×20 computing speed-up at an equivalent classification ratio when compared to classic SRM neuron membrane models. The proposed solution combines spike encoding, network topology, neuron membrane model and STDP learning.
Abstract-A dual current-regulated pulsewidth-modulated voltage-source inverter based on multiple two-phase PWM inverters, also called a B4 topology, requiring a dual ac-drive system with reduced switch count is proposed. The drive utilizes a total of only eight switches to produce two sets of three-phase or two-phase sinusoidal output currents that can be employed to feed three-phase or two-phase induction motors. A suitable control strategy of this new scheme is shown to minimize the single-phase current flow through the dc-link capacitors, which is a common problem in reduced-switch-count topologies. In order to verify the performance of the motor drive system, an application on traction of an electric vehicle is carried out. Results show that the ac current through the dc link can be minimized, and when utilizing two-phase motors on the proposed dual drive, the reduced voltage gain problem, also common in B4 topologies feeding three-phase motors, can be solved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.