Filters








777 Hits in 2.9 sec

A 28-nm Convolutional Neuromorphic Processor Enabling Online Learning with Spike-Based Retinas [article]

Charlotte Frenkel, Jean-Didier Legat, David Bol
2020 arXiv   pre-print
In order to leverage the data sparsity of spike-based neuromorphic retinas for adaptive edge computing and vision applications, we follow a top-down approach and propose SPOON, a 28-nm event-driven CNN  ...  sensors, a point that we further emphasize with N-MNIST benchmarking.  ...  CONCLUSION In this paper, we presented the SPOON event-driven CNN, following a top-down neuromorphic design approach.  ... 
arXiv:2005.06318v1 fatcat:n54tzllc7zbgjnii4jxtlaosxm

ST-MNIST – The Spiking Tactile MNIST Neuromorphic Dataset [article]

Hian Hian See, Brian Lim, Si Li, Haicheng Yao, Wen Cheng, Harold Soh, Benjamin C.K. Tee
2020 arXiv   pre-print
There is a dearth of neuromorphic event-based tactile datasets, principally due to the scarcity of large-scale event-based tactile sensors.  ...  The classification accuracies provided herein can serve as performance benchmarks for future work.  ...  The asynchronous event-driven mode of computing in SNNs has led to lower power consumption, and faster inference.  ... 
arXiv:2005.04319v1 fatcat:2jm3l3dnenchroxyz5x3lrq7zq

Recent trends in neuromorphic engineering

Sumit Soman, jayadeva, Manan Suri
2016 Big Data Analytics  
Neuromorphic Engineering has emerged as an exciting research area, primarily owing to the paradigm shift from conventional computing architectures to data-driven, cognitive computing.  ...  There is a diversity of work in the literature pertaining to neuromorphic systems, devices and circuits.  ...  [45] , event-driven vision processing by Yousefzadeh et al. [46] and Bayesian arithmetic stochastic synthesis by Duarte et al. [47] .  ... 
doi:10.1186/s41044-016-0013-1 fatcat:oyjitbviy5cdpesqwo6fp5tpgu

Dynamic Power Management for Neuromorphic Many-Core Systems

Sebastian Hoppner, Bernhard Vogginger, Yexin Yan, Andreas Dixius, Stefan Scholze, Johannes Partzsch, Felix Neumarker, Stephan Hartmann, Stefan Schiefer, Georg Ellguth, Love Cederstroem, Luis A. Plana (+3 others)
2019 IEEE Transactions on Circuits and Systems Part 1: Regular Papers  
This paper presents a dynamic power management architecture for neuromorphic many-core systems, such as SpiN-Naker.  ...  A numerical model of this power management model is derived which allows DVFS architecture exploration for neuromorphics.  ...  The proposed technique is also applicable to custom-digital neuromorphic systems which operate in an event-driven fashion. VI.  ... 
doi:10.1109/tcsi.2019.2911898 fatcat:hhlw2wl34zghrecivrhbqmu5ei

Dynamic Power Management for Neuromorphic Many-Core Systems [article]

Sebastian Hoeppner, Bernhard Vogginger, Yexin Yan, Andreas Dixius, Stefan Scholze, Johannes Partzsch, Felix Neumaerker, Stephan Hartmann, Stefan Schiefer, Georg Ellguth, Love Cederstroem, Luis Plana, Jim Garside (+2 others)
2019 arXiv   pre-print
This work presents a dynamic power management architecture for neuromorphic many core systems such as SpiNNaker.  ...  A numerical model of this power management model is derived which allows DVFS architecture exploration for neuromorphics.  ...  The proposed technique is also applicable to custom-digital neuromorphic systems which operate in an event-driven fashion.  ... 
arXiv:1903.08941v1 fatcat:5q4h54rr3zfulpkio72ot2lx7u

Hand-Gesture Recognition Based on EMG and Event-Based Camera Sensor Fusion: A Benchmark in Neuromorphic Computing

Enea Ceolini, Charlotte Frenkel, Sumit Bam Shrestha, Gemma Taverni, Lyes Khacef, Melika Payvand, Elisa Donati
2020 Frontiers in Neuroscience  
The proposed work represents a new benchmark that moves neuromorphic computing toward a real-world scenario.  ...  In particular, we used the event-based camera, called DVS, and two neuromorphic platforms, Loihi and ODIN + MorphIC.  ...  to Loihi neuromorphic platform.  ... 
doi:10.3389/fnins.2020.00637 pmid:32903824 pmcid:PMC7438887 fatcat:jbelvtolezbw7kamovfl6pxiam

NeMo

Mark Plagge, Christopher D. Carothers, Elsa Gonsiorowski
2016 Proceedings of the 2016 annual ACM Conference on SIGSIM Principles of Advanced Discrete Simulation - SIGSIM-PADS '16  
To address this question, an open-source neuromorphic processor architecture simulator called NeMo is being developed.  ...  Neuromorphic computing is a non-von Neumann architecture that mimics how the brain performs neural network types of computation in real hardware.  ...  In particular, the key contributions of this paper are: • The design and implementation of an event-driven neuromorphic processor architecture model that is able to execute in parallel using optimistic  ... 
doi:10.1145/2901378.2901392 dblp:conf/pads/PlaggeCG16 fatcat:hthmcz4mrrdjtn5mrhadakpz7u

Data-Driven Technology in Event-Based Vision

Ruolin Sun, Dianxi Shi, Yongjun Zhang, Ruihao Li, Ruoxiang Li
2021 Complexity  
Then, we explain why event-based data-driven technology becomes a research focus, including reasons for the rise of event-based vision and the superiority of data-driven approaches over other event-based  ...  Focusing on data-driven technology in event-based vision, this paper first explicates the operating principle, advantages, and intrinsic nature of event cameras, as well as background knowledge in event-based  ...  As mentioned in Section 4, event-based data-driven approaches are mainly divided into three categories: spiking neural networks, standard learning architectures, and novel architectures.  ... 
doi:10.1155/2021/6689337 doaj:0d0890fb649b4ea786696448a5c5966a fatcat:xrn7xoo3yrgetjhevfdnw76tiu

A Review of Current Neuromorphic Approaches for Vision, Auditory, and Olfactory Sensors

Anup Vanarse, Adam Osseiran, Alexander Rassau
2016 Frontiers in Neuroscience  
These sensors mimic the neuro-biological architecture of sensory organs using aVLSI (analog Very Large Scale Integration) and generate asynchronous spiking output that represents sensing information in  ...  To address these shortcomings, neuromorphic sensors have been developed.  ...  A thorough comparison between conventional cross-correlation approaches and spike-based sound localization algorithms shows that event-driven methods are about 40 times less computationally demanding .  ... 
doi:10.3389/fnins.2016.00115 pmid:27065784 pmcid:PMC4809886 fatcat:emxwvexhqndahd2qto25r7rzzi

Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware [article]

Christoph Ostrau, Jonas Homburg, Christian Klarhorst, Michael Thies, Ulrich Rückert
2020 arXiv   pre-print
With more and more event-based neuromorphic hardware systems being developed at universities and in industry, there is a growing need for assessing their performance with domain specific measures.  ...  This analysis is performed for five different networks, including three networks that have been found by an automated optimization with a neural architecture search framework.  ...  Neural Architecture Search (NAS) Lamarck ML 4 [11] is a modular and extensible Python library for application driven exploration of network architectures.  ... 
arXiv:2004.01656v2 fatcat:c3n3jgfvsbczxixlskvuvldcay

Classifying neuromorphic data using a deep learning framework for image classification [article]

Roshan Gopalakrishnan, Yansong Chua, Laxmi R Iyer
2018 arXiv   pre-print
These data are encoded in spike trains and hence seem ideal for benchmarking of neuromorphic learning algorithms.  ...  This raises the question of the suitability of such datasets as benchmarks for neuromorphic learning algorithms.  ...  But this also demonstrates the potential of combining neuromorphic sensors with deep learning architectures, so that we can take advantage of the event-driven nature of such sensors, and feeding the output  ... 
arXiv:1807.00578v1 fatcat:xhef6dmvlrhthoizd4vgrtf4fe

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

Mike Davies, Andreas Wild, Garrick Orchard, Yulia Sandamirskaya, Gabriel A. Fonseca Guerra, Prasad Joshi, Philipp Plank, Sumedh R. Risbud
2021 Proceedings of the IEEE  
Such spiking neural networks (SNNs) naturally provide energy efficiency by preferring inactive states and low-latency processing by operating in an asynchronous, event-driven manner.  ...  KEYWORDS | Computer architecture; neural network hardware; neuromorphics. I.  ...  Event-driven processing in neuromorphic hardware matches the temporal character and low-latency requirements of closed-loop control.  ... 
doi:10.1109/jproc.2021.3067593 fatcat:krqdmy3u6jdvfl7btjglek5ag4

RESPARC: A Reconfigurable and Energy-Efficient Architecture with Memristive Crossbars for Deep Spiking Neural Networks [article]

Aayush Ankit, Abhronil Sengupta, Priyadarshini Panda, Kaushik Roy
2017 arXiv   pre-print
Neuromorphic computing using post-CMOS technologies is gaining immense popularity due to its promising abilities to address the memory and power bottlenecks in von-Neumann computing systems.  ...  We evaluate the proposed architecture on different SNNs ranging in complexity from 2k-230k neurons and 1.2M-5.5M synapses.  ...  Effect of event-drivenness in SNNs The graphs in Fig. 13 show the energy savings for MNIST dataset on RESPARC due to SNN's event-driven processing nature.  ... 
arXiv:1702.06064v1 fatcat:mv75rfmiu5g7ri3hnrcru7jele

A Review of Algorithms and Hardware Implementations for Spiking Neural Networks

Duy-Anh Nguyen, Xuan-Tu Tran, Francesca Iacopi
2021 Journal of Low Power Electronics and Applications  
For hardware implementations, SNNs have attracted much attention in the neuromorphic hardware research community.  ...  SNN is the third generation of Artificial Neural Networks (ANNs), where each neuron in the network uses discrete spikes to communicate in an event-based manner.  ...  Neuromorphic computing is expected to lead ultimately to better energy efficiency compared to traditional computer architecture, due to the event-driven nature of the computation.  ... 
doi:10.3390/jlpea11020023 fatcat:rwhigu6tajeynabghkvszi5xa4

Benchmarking a Many-Core Neuromorphic Platform With an MPI-Based DNA Sequence Matching Algorithm

Gianvito Urgese, Francesco Barchi, Emanuele Parisi, Evelina Forno, Andrea Acquaviva, Enrico Macii
2019 Electronics  
SpiNNaker is a neuromorphic globally asynchronous locally synchronous (GALS) multi-core architecture designed for simulating a spiking neural network (SNN) in real-time.  ...  Exploiting this application, we benchmarked the SpiNNaker platform in terms of scalability and synchronisation latency.  ...  multiscale computation in neuromorphic hybrid systems FED Fast string matching method for Encoded DNA sequences  ... 
doi:10.3390/electronics8111342 fatcat:yjsmlxwqtrh2pht53mcz3wux2e
« Previous Showing results 1 — 15 out of 777 results