Redirigiendo al acceso original de articulo en 23 segundos...
ARTÍCULO
TITULO

On Spiking Neural Networks

Vladimir Evgrafov    
Eugene Ilyushin    

Resumen

Over the past few years, deep learning methods have made significant progress and have become widespread tools for solving various cognitive tasks. To leverage the power of deep learning everywhere, you need to deploy deep learning not only to large-scale computers but also to peripherals. However, the ever-growing  complexity of deep neural networks, coupled with a dramatic increase in the amount of data processed, place significant energy demands on  modern computing  platforms. The neuromorphic computing model assumes that computations are performed in a biologically plausible way. Part of neuromorphic computing is spike neural networks, which are one of the leading candidates for overcoming the limitations of neural computing and effectively using machine learning algorithms in real-world applications. This paper discusses the biological foundations of spike neural networks, methods for training and creating them, as well as software and hardware platforms for their use.

 Artículos similares

       
 
Farzad Nikfam, Raffaele Casaburi, Alberto Marchisio, Maurizio Martina and Muhammad Shafique    
Revista: Information

 
Arash Khajooei Nejad, Mohammad (Behdad) Jamshidi and Shahriar B. Shokouhi    
This paper introduces Tensor-Organized Memory (TOM), a novel neuromorphic architecture inspired by the human brain?s structural and functional principles. Utilizing spike-timing-dependent plasticity (STDP) and Hebbian rules, TOM exhibits cognitive behavi... ver más
Revista: Computers

 
Octavio Delgadillo, Bernhard Blieninger, Juri Kuhn and Uwe Baumgarten    
Consolidating tasks to a smaller number of electronic control units (ECUs) is an important strategy for optimizing costs and resources in the automotive industry. In our research, we aim to enable ECU consolidation by migrating tasks at runtime between d... ver más

 
Leonardo Lucio Custode, Hyunho Mo, Andrea Ferigo and Giovanni Iacca    
Remaining useful life (RUL) prediction is a key enabler for predictive maintenance. In fact, the possibility of accurately and reliably predicting the RUL of a system, based on a record of its monitoring data, can allow users to schedule maintenance inte... ver más
Revista: Algorithms

 
Huynh Cong Viet Ngu and Keon Myung Lee    
Due to energy efficiency, spiking neural networks (SNNs) have gradually been considered as an alternative to convolutional neural networks (CNNs) in various machine learning tasks. In image recognition tasks, leveraging the superior capability of CNNs, t... ver más
Revista: Applied Sciences