Search results for "Neuromorphic"

showing 6 items of 16 documents

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…

Spiking neural networkComputer sciencebusiness.industrySpike trainImage processingVideo processingEdge detectionNeuromorphic engineeringEncoding (memory)Computer visionSpike (software development)Artificial intelligencebusinessComputer hardware2014 IX Southern Conference on Programmable Logic (SPL)
researchProduct

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…

Spiking neural networkQuantitative Biology::Neurons and CognitionComputer scienceNoise (signal processing)General MathematicsApplied MathematicsGeneral Physics and AstronomyStatistical and Nonlinear PhysicsEngramMemristorStochastic processeSignalNeural networklaw.inventionNoise induced phenomenaNeuromorphic engineeringlawVoltage spikeMemristive devicesState (computer science)Biological system
researchProduct

Towards peptide-based tunable multistate memristive materials

2021

Development of new memristive hardware is a technological requirement towards widespread neuromorphic computing. Molecular spintronics seems to be a fertile field for the design and preparation of this hardware. Within molecular spintronics, recent results on metallopeptides demonstrating the interaction between paramagnetic ions and the chirality induced spin selectivity effect hold particular promise for developing fast (ns–μs) operation times. [R. Torres-Cavanillas et al., J. Am. Chem. Soc., 2020, DOI: 10.1021/jacs.0c07531]. Among the challenges in the field, a major highlight is the difficulty in modelling the spin dynamics in these complex systems, but at the same time the use of inexp…

SpintronicsSpin dynamicsBase SequenceComputer scienceUNESCO::QUÍMICAComplex systemGeneral Physics and AstronomyNanotechnology02 engineering and technologyMemristor010402 general chemistry021001 nanoscience & nanotechnology01 natural sciencesLanthanoid Series Elements:QUÍMICA [UNESCO]0104 chemical scienceslaw.inventionNeuromorphic engineeringlawMetalloproteinsAmino Acid SequenceNeural Networks ComputerPhysical and Theoretical Chemistry0210 nano-technologyPeptides
researchProduct

Visual spike-based convolution processing with a Cellular Automata architecture

2010

this paper presents a first approach for implementations which fuse the Address-Event-Representation (AER) processing with the Cellular Automata using FPGA and AER-tools. This new strategy applies spike-based convolution filters inspired by Cellular Automata for AER vision processing. Spike-based systems are neuro-inspired circuits implementations traditionally used for sensory systems or sensor signal processing. AER is a neuromorphic communication protocol for transferring asynchronous events between VLSI spike-based chips. These neuro-inspired implementations allow developing complex, multilayer, multichip neuromorphic systems and have been used to design sensor chips, such as retinas an…

Very-large-scale integrationSignal processingTheoretical computer scienceArtificial neural networkComputer sciencebusiness.industrySensory systemCellular automatonConvolutionNeuromorphic engineeringAsynchronous communicationSpike (software development)businessComputer hardwareThe 2010 International Joint Conference on Neural Networks (IJCNN)
researchProduct

AER Filtering Using GLIDER: VHDL Cellular Automata Description

2008

Cellular Automata (CA) is a bio-inspired processing model for problem solving, initially proposed by Von Neumann. This approach modularizes the processing by dividing the solution into synchronous cells that change their states at the same time in order to get the solution. The communication between them is crucial to achieve the correct solution. On the other hand, the Address-Event-Representation (AER) is a neuromorphic communication protocol for transferring asynchronous events between VLSI chips. These neuro-inspired implementations have been used to design sensor chips (retina, cochleas), processing chips (convolutions, filters) and learning chips, which makes it possible to develop co…

Very-large-scale integrationbusiness.industryComputer scienceHardware description languageFilter (signal processing)Cellular automatonNeuromorphic engineeringAsynchronous communicationEmbedded systemVHDLbusinesscomputerDigital filterComputer hardwarecomputer.programming_language
researchProduct

Less Data Same Information for Event-Based Sensors: A Bioinspired Filtering and Data Reduction Algorithm

2018

Sensors provide data which need to be processed after acquisition to remove noise and extract relevant information. When the sensor is a network node and acquired data are to be transmitted to other nodes (e.g., through Ethernet), the amount of generated data from multiple nodes can overload the communication channel. The reduction of generated data implies the possibility of lower hardware requirements and less power consumption for the hardware devices. This work proposes a filtering algorithm (LDSI&mdash

bioinspired event filteringComputer sciencedynamic vision sensor02 engineering and technologylcsh:Chemical technology01 natural sciencesBiochemistryArticleAnalytical ChemistryReduction (complexity)0202 electrical engineering electronic engineering information engineeringneuromorphic systemslcsh:TP1-1185Electrical and Electronic EngineeringEnginyeria DissenyInstrumentationEnginyeria elèctricaEvent (computing)Noise (signal processing)010401 analytical chemistryFilter (signal processing)Atomic and Molecular Physics and Optics0104 chemical sciencesevent data reductionFPGA implementationspike-basedLookup table020201 artificial intelligence & image processingevent-based sensorsAlgorithmData reductionSensors
researchProduct