Search results for "NEURAL NETWORK"
showing 10 items of 1385 documents
Performance evaluation of fuzzy-neural HTTP request distribution for Web clusters
2006
In this paper we present the performance evaluation of our fuzzy-neural HTTP request distribution algorithm called FNRD, which assigns each incoming request to the server in the Web cluster with the quickest expected response time. The fuzzy mechanism is used to estimate the expected response times. A neural-based feedback loop is used for real-time tuning of response time estimates. To evaluate the system, we have developed a detailed simulation and workload model using CSIM19 package. Our simulations show that FNRD can be more effective than its competitors.
Neural network prediction of AE data
1997
Neural network (NN) models were constructed to study prediction of the AE index. Both solar wind (vBz) and previous observed AE inputs were used to predict AE data for different numbers of time steps ahead. It seems that prediction of the original unsmoothed AE data is possible only for 10 time steps (25 min) ahead. The predicted time series of the AE data for 50 time steps (125 min) ahead was found to be dynamically different from the original time series. It is possible that the NN model cannot reproduce the turbulent part of the power spectrum of the AE data. However, when using smoothed AE data the prediction for 10 time steps ahead gave an NMSE of 0.0438, and a correlation coefficient …
A spiking network for spatial memory formation: Towards a fly-inspired ellipsoid body model
2013
Neural centers devoted to spatial memory and path integration were largely studied in rats and in different insect species like ants and bees. In this paper a neural-based model for the formation of a spatial working memory is proposed mirroring some peculiarities of the Drosophila central brain and in particular the ellipsoid body. Simulation results are reported opening the way to applications on roving platforms.
Interaction in Spoken Word Recognition Models: Feedback Helps
2018
Human perception, cognition, and action requires fast integration of bottom-up signals with top-down knowledge and context. A key theoretical perspective in cognitive science is the interactive activation hypothesis: forward and backward flow in bidirectionally connected neural networks allows humans and other biological systems to approximate optimal integration of bottom-up and top-down information under real-world constraints. An alternative view is that online feedback is neither necessary nor helpful; purely feed forward alternatives can be constructed for any feedback system, and online feedback could not improve processing and would preclude veridical perception. In the domain of spo…
Hardware-accelerated spike train generation for neuromorphic image and video processing
2014
Recent studies concerning Spiking Neural Networks show that they are a powerful tool for multiple applications as pattern recognition, image tracking, and detection tasks. The basic functional properties of SNN reside in the use of spike information encoding as the neurons are specifically designed and trained using spike trains. We present a novel and efficient frequency encoding algorithm with Gabor-like receptive fields using probabilistic methods and targeted to FPGA for online pro-cessing. The proposed encoding is versatile, modular and, when applied to images, it is able to perform simple image transforms as edge detection, spot detection or removal, and Gabor-like filtering without a…
FPGA implementation of Spiking Neural Networks supported by a Software Design Environment
2011
Abstract This paper is focused on the creation of Spiking Neural Networks (SNN) in hardware due to their advantages for certain problem solving and their similarity to biological neural system. One of the main uses of this neural structure is pattern classification. The chosen model for the spiking neuron is the Spike Response Model (SRM). For SNN design and implementation, a software application has been developed to provide easy creation, simulation and automatic generation of the hardware model. VHDL was used for the hardware model. This paper describes the functionality of SNN and the design procedure followed to obtain a working neural system in both software and hardware. Designed VHD…
FPGA implementation of Spiking Neural Networks
2012
Abstract Spiking Neural Networks (SNN) have optimal characteristics for hardware implementation. They can communicate among neurons using spikes, which in terms of logic resources, means a single bit, reducing the logic occupation in a device. Additionally, SNN are similar in performance compared to other neural Artificial Neural Network (ANN) architectures such as Multilayer Perceptron, and others. SNN are very similar to those found in the biological neural system, having weights and delays as adjustable parameters. This work describes the chosen models for the implemented SNN: Spike Response Model (SRM) and temporal coding is used. FPGA implementation using VHDL language is also describe…
Simplified spiking neural network architecture and STDP learning algorithm applied to image classification
2015
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) lear…
Noise-assisted persistence and recovery of memory state in a memristive spiking neuromorphic network
2021
Abstract We investigate the constructive role of an external noise signal, in the form of a low-rate Poisson sequence of pulses supplied to all inputs of a spiking neural network, consisting in maintaining for a long time or even recovering a memory trace (engram) of the image without its direct renewal (or rewriting). In particular, this unique dynamic property is demonstrated in a single-layer spiking neural network consisting of simple integrate-and-fire neurons and memristive synaptic weights. This is carried out by preserving and even fine-tuning the conductance values of memristors in terms of dynamic plasticity, specifically spike-timing-dependent plasticity-type, driven by overlappi…
Fast spiking neural network architecture for low-cost FPGA devices
2012
Spiking Neural Networks (SNN) consist of fully interconnected computation units (neurons) based on spike processing. This type of networks resembles those found in biological systems studied by neuroscientists. This paper shows a hardware implementation for SNN. First, SNN require the inputs to be spikes, being necessary a conversion system (encoding) from digital values into spikes. For travelling spikes, each neuron interconnection is characterized by weights and delays, requiring an internal neuron processing by a Postsynaptic Potential (PSP) function and membrane potential threshold evaluation for a postsynaptic output spike generation. In order to model a real biological system by arti…