Filters








88 Hits in 8.3 sec

A Digital Neuromorphic Architecture Efficiently Facilitating Complex Synaptic Response Functions Applied to Liquid State Machines [article]

Michael R. Smith, Aaron J. Hill, Kristofor D. Carlson, Craig M. Vineyard, Jonathon Donaldson, David R. Follett, Pamela L. Follett, John H. Naegle, Conrad D. James, James B. Aimone
2017 arXiv   pre-print
In this paradigm we examine liquid state machines applied to speech recognition and show how a liquid state machine with temporal dynamics maps onto the STPU-demonstrating the flexibility and efficiency  ...  Inspired by neuroscience principles, we present a digital neuromorphic architecture, the Spiking Temporal Processing Unit (STPU), capable of modeling arbitrary complex synaptic response functions without  ...  We also examine liquid state machines (LSMs) [11] to show how the constructs available in the STPU facilitate complex dynamical neuronal systems.  ... 
arXiv:1704.08306v1 fatcat:mvg6m7g5vnddtftd24kyawo56m

Protein Structured Reservoir computing for Spike-based Pattern Recognition [article]

Karolos-Alexandros Tsakalos, Georgios Ch. Sirakoulis, Andrew Adamatzky, Jim Smith
2020 arXiv   pre-print
We apply on a single readout layer various training methods in a supervised fashion to investigate whether the molecular structured Reservoir Computing (RC) system is capable to deal with machine learning  ...  demanding for novel devices.  ...  ) pattern recognition training algorithm in a supervised fashion on a single output layer of spiking neurons, which is found mainly in echo state networks and not in liquid state machines we use here,  ... 
arXiv:2008.03330v1 fatcat:fjzlh7ta65gvdpyr44xz7mik3a

Electrolyte-gated transistors for synaptic electronics, neuromorphic computing, and adaptable biointerfacing

Haifeng Ling, Dimitrios A. Koutsouras, Setareh Kazemzadeh, Yoeri van de Burgt, Feng Yan, Paschalis Gkoupidenis
2020 Applied Physics Reviews  
This endows synaptic circuits with concurrent actualization of inference and learning, hence facilitating the implementation of more complex neuromorphic functions. 57 Besides, the write current (i.e  ...  NEUROMORPHIC DEVICES AND FUNCTIONS The biologically inspired neuromorphic systems are expected to be capable of dealing with complex and intelligent tasks, where neuromorphic functionalities need to be  ... 
doi:10.1063/1.5122249 fatcat:toitkrqdgbg6boldbcveiqqfvu

Roadmap on emerging hardware and technology for machine learning

Qiangfei Xia, Karl K Berggren, Konstantin Likharev, Dmitri B Strukov, Hao Jiang, Thomas Mikolajick, Damien Querlioz, Martin Salinga, John Erickson, Shuang Pi, Feng Xiong, Peng Lin (+31 others)
2020 Nanotechnology  
Data-centric computing requires a revolution in hardware systems, since traditional digital computers based on transistors and the von Neumann architecture were not purposely designed for neuromorphic  ...  A hardware platform based on emerging devices and new architecture is the hope for future computing with dramatically improved throughput and energy efficiency.  ...  Acknowledgments This is a contribution of NIST, an agency of the US government, not subject to copyright.  ... 
doi:10.1088/1361-6528/aba70f pmid:32679577 fatcat:t6me4pfxgfhdvbdqjnyjuksf2e

2022 Roadmap on Neuromorphic Computing and Engineering [article]

Dennis V. Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+47 others)
2022 arXiv   pre-print
The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic  ...  built-in capabilities to learn or deal with complex data as our brain does.  ...  Concluding Remarks Integrating event-based vision sensing and processing with neuromorphic computation techniques is expected to yield solutions that will be able to penetrate the artificial vision market  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4

Spiking Neural Networks Hardware Implementations and Challenges

Maxence Bouvier, Alexandre Valentian, Thomas Mesquida, Francois Rummens, Marina Reyboz, Elisa Vianello, Edith Beigne
2019 ACM Journal on Emerging Technologies in Computing Systems  
As opposed to Von Neumann machines, brain-inspired processors aim at bringing closer the memory and the computational elements to efficiently evaluate machine-learning algorithms.  ...  Neuromorphic computing is henceforth a major research field for both academic and industrial actors.  ...  Finally, a specific type of spiking networks, called liquid state machines (LSMs) or reservoir networks, fully takes its inspiration from the brain.  ... 
doi:10.1145/3304103 fatcat:p3frra3osnhybj4hkor4y5cyqm

Integration of nanoscale memristor synapses in neuromorphic computing architectures

Giacomo Indiveri, Bernabé Linares-Barranco, Robert Legenstein, George Deligeorgis, Themistoklis Prodromakis
2013 Nanotechnology  
In this paper, we first review the neuro- and neuromorphic-computing approaches that can best exploit the properties of memristor and-scale devices, and then propose a novel hybrid memristor-CMOS neuromorphic  ...  element and the low energy required to write distinct states.  ...  Acknowledgment This work was supported by the European CHIST-ERA program, via the "Plasticity in NEUral Memristive Architectures" (PNEUMA) project.  ... 
doi:10.1088/0957-4484/24/38/384010 pmid:23999381 fatcat:6isdvp5f4vhgddskpmlx2xq5ra

Unsupervised heart-rate estimation in wearables with Liquid states and a probabilistic readout

Anup Das, Paruthi Pradhapan, Willemijn Groenendaal, Prathyusha Adiraju, Raj Thilak Rajan, Francky Catthoor, Siebren Schaafsma, Jeffrey L. Krichmar, Nikil Dutt, Chris Van Hoof
2018 Neural Networks  
computation model; (2) a novel learning algorithm; and (3) an intelligently designed unsupervised readout based on Fuzzy c-Means clustering of spike responses from a subset of neurons (Liquid states),  ...  The novelty of our approach lies in (1) encoding spatio-temporal properties of ECG signals directly into spike train and using this to excite recurrently connected spiking neurons in a Liquid State Machine  ...  Responsive Technologies aNd Engagement togetheR).  ... 
doi:10.1016/j.neunet.2017.12.015 pmid:29414535 fatcat:3y3dvm5ezvg77ij2g3ukes4vpa

Memristors – from In-memory computing, Deep Learning Acceleration, Spiking Neural Networks, to the Future of Neuromorphic and Bio-inspired Computing [article]

Adnan Mehonic, Abu Sebastian, Bipin Rajendran, Osvaldo Simeone, Eleni Vasilaki, Anthony J. Kenyon
2020 arXiv   pre-print
This paper reviews the case for a novel beyond CMOS hardware technology, memristors, as a potential solution for the implementation of power-efficient in-memory computing, deep learning accelerators, and  ...  Deep learning is based on computational models that are, to a certain extent, bio-inspired, as they rely on networks of connected simple computing units operating in parallel.  ...  Common in the approaches of echo state networks and liquid state machines is the idea of using a randomly recurrent network with fixed connectivity, hence no need to resort to backpropagation through time  ... 
arXiv:2004.14942v1 fatcat:b52hrjk365f2tabarxg4zfys44

Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization [article]

Wenrui Zhang, Peng Li
2021 arXiv   pre-print
In neural circuits, recurrent connectivity plays a crucial role in network function and stability.  ...  We aim to enable systemic design of large RSNNs via a new scalable RSNN architecture and automated architectural optimization.  ...  Only recently, [29] adopted a simulated annealing algorithm to learn the optimal hyperparameters of liquid state machine (LSM) models through a three-step search.  ... 
arXiv:2108.01793v1 fatcat:ynp773e54vf4pjlkw222o4ju4m

The Rise of Bioinspired Ionotronics

Changjin Wan, Kai Xiao, Alessandro Angelin, Markus Antonietti, Xiaodong Chen
2019 Advanced Intelligent Systems  
Translational implementation of ionotronics gives birth to a wide range of novel and exciting paradigm breakers, which greatly innovates the development of the bio-technology interface.  ...  Despite its infancy, bioinspired ionotronics exhibit an unprecedented potential to advance a broad spectrum of applications such as robotics, neuromorphic engineering, and biosensing and readouts.  ...  Acknowledgements C.W. and K.X. contributed equally to this work.  ... 
doi:10.1002/aisy.201900073 fatcat:qxt2qv67vrhxfffb7ohnwdskx4

Mapping Spiking Neural Networks to Neuromorphic Hardware [article]

Adarsha Balaji, Anup Das, Yuefeng Wu, Khanh Huynh, Francesco Dell'Anna, Giacomo Indiveri, Jeffrey L. Krichmar, Nikil Dutt, Siebren Schaafsma, Francky Catthoor
2019 arXiv   pre-print
Neuromorphic hardware platforms implement biological neurons and synapses to execute spiking neural networks (SNNs) in an energy-efficient manner.  ...  We present SpiNeMap, a design methodology to map SNNs to crossbar-based neuromorphic hardware, minimizing spike latency and energy consumption.  ...  For other architectures such as the Liquid State Machine (LSM) [27] , ISI of critical neurons contribute to the accuracy.  ... 
arXiv:1909.01843v1 fatcat:w4kpthbfcvbjpiw7oue7bxcpyq

Memristors—From In‐Memory Computing, Deep Learning Acceleration, and Spiking Neural Networks to the Future of Neuromorphic and Bio‐Inspired Computing

Adnan Mehonic, Abu Sebastian, Bipin Rajendran, Osvaldo Simeone, Eleni Vasilaki, Anthony J. Kenyon
2020 Advanced Intelligent Systems  
Common in the approaches of echo state networks and liquid state machines is the idea of using a randomly recurrent network with fixed connectivity, hence no need to resort to backpropagation through time  ...  More complex functionalities (neuromorphic), beyond simple digital switching CMOS paradigm, directly implemented in memristive hardware primitives, might fuel the next wave of higher cognitive systems.  ... 
doi:10.1002/aisy.202000085 fatcat:3ov6ahzlvjhlbn7bvvfnzmf26e

Recent advances in physical reservoir computing: A review

Gouhei Tanaka, Toshiyuki Yamane, Jean Benoit Héroux, Ryosho Nakane, Naoki Kanazawa, Seiji Takeda, Hidetoshi Numata, Daiju Nakano, Akira Hirose
2019 Neural Networks  
It is derived from several recurrent neural network models, including echo state networks and liquid state machines.  ...  A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir.  ...  Acknowledgments We would like to thank Ze Hei for his assistance in collecting the relevant papers and the anonymous reviewers for helpful comments that improved the quality of this review.  ... 
doi:10.1016/j.neunet.2019.03.005 fatcat:u4vjykpyxnch3n24kprqoi2tsy

Deep learning in spiking neural networks

Amirhossein Tavanaei, Masoud Ghodrati, Saeed Reza Kheradpisheh, Timothée Masquelier, Anthony Maida
2019 Neural Networks  
In recent years, deep learning has been a revolution in the field of machine learning, for computer vision in particular.  ...  SNNs are also more hardware friendly and energy-efficient than ANNs, and are thus appealing for technology, especially for portable devices. However, training deep SNNs remains a challenge.  ...  Liquid State Machines and Reservoirs: The neocortex, unique to mammals, has the ability to drastically scale its surface area from about 1 square cm in the mouse to about 2,500 square cm in the human  ... 
doi:10.1016/j.neunet.2018.12.002 fatcat:nfat4xwh5bdtfhauugyqpxhnzq
« Previous Showing results 1 — 15 out of 88 results