English
Related papers

Related papers: Spoken Digit Classification by In-Materio Reservoi…

200 papers

The deployment of Artificial Intelligence on edge devices (TinyML) is often constrained by the high power consumption and latency associated with traditional Artificial Neural Networks (ANNs) and their reliance on intensive Matrix-Multiply…

Hardware Architecture · Computer Science 2026-01-21 Debabrata Das , Yogeeth G. K. , Arnav Gupta

Bio-inspired neuromorphic hardware is a research direction to approach brain's computational power and energy efficiency. Spiking neural networks (SNN) encode information as sparsely distributed spike trains and employ…

Emerging Technologies · Computer Science 2018-10-23 Haowem Fang , Amar Shrestha , De Ma , Qinru Qiu

In this work, we have proposed a revolutionary neuromorphic computing methodology to implement All-Skyrmion Spiking Neural Network (AS-SNN). Such proposed methodology is based on our finding that skyrmion is a topological stable spin…

Neural and Evolutionary Computing · Computer Science 2017-05-09 Zhezhi He , Deliang Fan

Topic classification systems on spoken documents usually consist of two modules: an automatic speech recognition (ASR) module to convert speech into text and a text topic classification (TTC) module to predict the topic class from the…

Computation and Language · Computer Science 2021-06-17 Tan Liu , Wu Guo , Bin Gu

The spiking neural network (SNN) computes and communicates information through discrete binary events. It is considered more biologically plausible and more energy-efficient than artificial neural networks (ANN) in emerging neuromorphic…

Neural and Evolutionary Computing · Computer Science 2021-05-28 Yang Li , Yi Zeng , Dongcheng Zhao

Spintronic nanodevices have ultrafast nonlinear dynamic and recurrence behaviors on a nanosecond scale that promises to enable spintronic reservoir computing (RC) system. Here two physical RC systems based on a single magnetic skyrmion…

Emerging Technologies · Computer Science 2020-10-28 Wencong Jiang , Lina Chen , Kaiyuan Zhou , Liyuan Li , Qingwei Fu , Youwei Du , Ronghua Liu

Spiking Neural Networks (SNNs) offer an event-driven and more biologically realistic alternative to standard Artificial Neural Networks based on analog information processing. This can potentially enable energy-efficient hardware…

Emerging Technologies · Computer Science 2019-02-06 Indranil Chakraborty , Gobinda Saha , Kaushik Roy

Reservoir Computing is a type of recursive neural network commonly used for recognizing and predicting spatio-temporal events relying on a complex hierarchy of nested feedback loops to generate a memory functionality. The Reservoir…

Mesoscale and Nanoscale Physics · Physics 2018-02-05 George Bourianoff , Daniele Pinna , Matthias Sitte , Karin Everschor-Sitte

Deep neural networks have been proven to be highly effective tools in various domains, yet their computational and memory costs restrict them from being widely deployed on portable devices. The recent rapid increase of edge computing…

Neural and Evolutionary Computing · Computer Science 2023-06-01 Ayan Shymyrbay , Mohammed E. Fouda , Ahmed Eltawil

Recently, artificial-intelligence (AI) technologies have been increasingly utilized in a wide range of real-world applications. Speech recognition is one of these practical AI tasks and is regarded as a key application for edge AI systems.…

Deep learning has driven significant technological advancements, but its high energy consumption limits its use on battery-operated edge devices. Spiking Neural Networks (SNNs) offer promising reductions in inference-time energy…

Hardware Architecture · Computer Science 2026-04-21 Zhanglu Yan , Zhenyu Bai , Tulika Mitra , Weng-Fai Wong

Solid state ionic conductors are good candidates for the next generation of nonvolatile computer memory elements. Such devices have to show reproducible resistance switching at reasonable voltage and current values even if scaled down to…

Mesoscale and Nanoscale Physics · Physics 2011-04-25 A. Geresdi , A. Halbritter , A. Gyenis , P. Makk , G. Mihály

Neuromorphic hardware facilitates rapid and energy-efficient training and operation of neural network models for artificial intelligence. However, existing analog in-memory computing devices, like memristors, continue to face significant…

The scaling limitations of conventional transistors demand alternative device concepts capable of dynamic reconfigurability at the atomic scale. Resistive switching (RS), a key mechanism for neuromorphic computing and non-volatile memory,…

Neuromorphic computing, commonly understood as a computing approach built upon neurons, synapses, and their dynamics, as opposed to Boolean gates, is gaining large mindshare due to its direct application in solving current and future…

Emerging Technologies · Computer Science 2023-05-09 Md Golam Morshed , Samiran Ganguly , Avik W. Ghosh

An accurate objective speech intelligibility prediction algorithms is of great interest for many applications such as speech enhancement for hearing aids. Most algorithms measures the signal-to-noise ratios or correlations between the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-07 Zehai Tu , Ning Ma , Jon Barker

Problem statement: This paper examines Artificial Spiking Neural Network (ASNN) which inter-connects group of artificial neurons that uses a mathematical model with the aid of block cipher. The aim of undertaken this research is to come up…

Cryptography and Security · Computer Science 2010-08-31 Saleh Ali K. Al-Omari , Putra Sumari

Computation in biological neural circuits arises from the interplay of nonlinear temporal responses and spatially distributed dynamic network interactions. Replicating this richness in hardware has remained challenging, as most neuromorphic…

Resistive memories (RRAM) are promising candidates for replacing present nonvolatile memories and realizing storage class memories; hence resistance switching devices are of particular interest. These devices are typically memristive, with…

Applied Physics · Physics 2025-02-06 N Vasileiadis , P Loukas , A Mavropoulis , P Normand , I Karafyllidis , G Ch Sirakoulis , P Dimitrakis

Wireless spiking neural networks (WSNNs) allow energy-efficient communications, especially when considering edge intelligence and learning for both terrestrial beyond 5G/6G and space networking systems. Recent research work has revealed…

Signal Processing · Electrical Eng. & Systems 2025-01-31 Pietro Savazzi , Anna Vizziello , Fabio Dell'Acqua
‹ Prev 1 4 5 6 7 8 10 Next ›