Filters








38 Hits in 3.1 sec

Evolving unipolar memristor spiking neural networks

David Howard, Larry Bull, Ben De Lacy Costello
2015 Connection science  
MEMRISTIVE SPIKING NETWORKS Spiking Neural Networks (SNNs) model neural activity in the brain to varying degrees of precision.  ...  In this paper we simulate and analyse unipolar memristor networks, and ascertain the suitability of the unipolar memristor when used as an alternative to the bipolar memristor as a synapse in spiking neural  ... 
doi:10.1080/09540091.2015.1080225 fatcat:kojxpcr2wbgd5aus6mvvcrihqy

Evolving Unipolar Memristor Spiking Neural Networks [article]

David Howard, Larry Bull, Ben De Lacy Costello
2015 arXiv   pre-print
Experimentation on a two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant nonplastic connections  ...  In this paper we consider the Unipolar memristor synapse --- a device capable of non-Hebbian switching between only two states (conductive and resistive) through application of a suitable input voltage  ...  MEMRISTIVE SPIKING NETWORKS Spiking Neural Networks (SNNs) model neural activity in the brain to varying degrees of precision.  ... 
arXiv:1509.00105v1 fatcat:ziepyrsvbbca5fvmufqqlbkuzq

Evolving Unipolar Memristor Spiking Neural Networks [chapter]

David Howard, Larry Bull, Ben de Lacy Costello
2015 Lecture Notes in Computer Science  
MEMRISTIVE SPIKING NETWORKS Spiking Neural Networks (SNNs) model neural activity in the brain to varying degrees of precision.  ...  In this paper we simulate and analyse unipolar memristor networks, and ascertain the suitability of the unipolar memristor when used as an alternative to the bipolar memristor as a synapse in spiking neural  ... 
doi:10.1007/978-3-319-14803-8_20 fatcat:zgvqx7xi7rablnddmwi3rfw4ly

Supervised learning with organic memristor devices and prospects for neural crossbar arrays

Christopher H. Bennett, Djaafar Chabi, Theo Cabaret, Bruno Jousselme, Vincent Derycke, Damien Querlioz, Jacques-Olivier Klein
2015 Proceedings of the 2015 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH´15)  
In this work, we highlight that these two features can be beneficial for neural network-inspired learning systems.  ...  An on-chip supervised learning method for hybrid memristors / CMOS systems -an analogue synaptic array paired with a hybrid learning cell -is extended to the case of this novel organic memristor device  ...  artifical neural networks [11] .  ... 
doi:10.1109/nanoarch.2015.7180609 dblp:conf/nanoarch/BennettCCJDQK15 fatcat:ir2se6mbqvew3olq6ogzljr2ai

STDP and STDP variations with memristors for spiking neuromorphic learning systems

T. Serrano-Gotarredona, T. Masquelier, T. Prodromakis, G. Indiveri, B. Linares-Barranco
2013 Frontiers in Neuroscience  
In the approaches described, neurons fire spikes asynchronously when they wish and memristive synapses perform computation and learn at their own pace, as it happens in biological neural systems.  ...  In this paper we review several ways of realizing asynchronous Spike-Timing-Dependent-Plasticity (STDP) using memristors as synapses.  ...  MEMRISTORS AND CMOS NEURONS FOR SINGLE-SPIKE STDP For the case of the alternative single-spike Spiking Neural Network Network of neurons that interchange information among them using "spikes."  ... 
doi:10.3389/fnins.2013.00002 pmid:23423540 pmcid:PMC3575074 fatcat:7sscocmhsrh6fmqsje72makuzq

CMOS and Memristive Hardware for Neuromorphic Computing

Mostafa Rahimi Azghadi, Ying-Chen Chen, Jason K. Eshraghian, Jia Chen, Chih-Yang Lin, Amirali Amirsoleimani, Adnan Mehonic, Anthony J Kenyon, Burt Fowler, Jack C. Lee, Yao-Feng Chang
2020 Advanced Intelligent Systems  
neural networks.  ...  We have studied extensively the effects of various memristors' nonidealities on inference accuracy, using the MNIST handwritten digits dataset, [51] where the neural network weights are represented as  ... 
doi:10.1002/aisy.201900189 fatcat:lrspxweqlfb6bmmqir6mwzvx44

Challenges in materials and devices for Resistive-Switching-based Neuromorphic Computing [article]

Javier del Valle, Juan Gabriel Ramírez, Marcelo J. Rozenberg and Ivan K. Schuller
2018 arXiv   pre-print
STDP functionality is at the root of learning algorithms for spiking neural networks.  ...  These two functionalities are the essential components of any neural network.  ... 
arXiv:1812.01120v1 fatcat:pi3oapmwhfe4paiajgp7zrvway

Bioinspired bio-voltage memristors

Tianda Fu, Xiaomeng Liu, Hongyan Gao, Joy E. Ward, Xiaorong Liu, Bing Yin, Zhongrui Wang, Ye Zhuo, David J. F. Walker, J. Joshua Yang, Jianhan Chen, Derek R. Lovley (+1 others)
2020 Nature Communications  
The potential of using the memristor to directly process biosensing signals is also demonstrated.  ...  Artificial neurons built from these memristors not only function at biological action potentials (e.g., 100 mV, 1 ms) but also exhibit temporal integration close to that in biological neurons.  ...  neural networks 14 .  ... 
doi:10.1038/s41467-020-15759-y pmid:32313096 fatcat:n7qyxudubve73eswzknsjgk73u

Nonvolatile Memories in Spiking Neural Network Architectures: Current and Emerging Trends

M. Lakshmi Varshika, Federico Corradi, Anup Das
2022 Electronics  
Neuromorphic systems mimic biological functions by employing spiking neural networks for achieving brain-like efficiency, speed, adaptability, and intelligence.  ...  This review collects the most recent trends in exploiting the physical properties of nonvolatile memory technologies for implementing efficient in-memory and in-device computing with spike-based neuromorphic  ...  (B) Spiking neural network with spike-based learning implemented through NVMs. (C) Crossbar array for spiking neural network.  ... 
doi:10.3390/electronics11101610 fatcat:x4aqw2xk55g5tmdfqvygyxh5eu

Proposal For Neuromorphic Hardware Using Spin Devices [article]

Mrigank Sharad, Charles Augustine, Georgios Panagopoulos, Kaushik Roy
2012 arXiv   pre-print
Magnetic tunnel junctions are employed for interfacing the spin-neurons with charge-based devices like CMOS, for large-scale networks.  ...  Integrating Neuron Using Domain Wall Magnets Spiking neural network is the most recent and evolving topology of neural networks.  ...  Fig. 14 shows a cross-bar neural network architecture using memristor (/PCM) synapses and bipolar spin neurons.  ... 
arXiv:1206.3227v4 fatcat:kxg3gag6k5drxadtyt4cbq3dma

Towards Neuromorphic Learning Machines Using Emerging Memory Devices with Brain-Like Energy Efficiency

Vishal Saxena, Xinyu Wu, Ira Srivastava, Kehan Zhu
2018 Journal of Low Power Electronics and Applications  
Practical demonstration of such architectures has been limited as performance of emerging memory devices falls short of the expected behavior from the idealized memristor-based analog synapses, or weights  ...  In this article, we review the challenges involved and present a pathway to realize large-scale mixed-signal NeuSoCs, from device arrays and circuits to spike-based deep learning algorithms with 'brain-like  ...  Neural Networks SNR Signal-to-Noise Ratio STDP Spike-  ... 
doi:10.3390/jlpea8040034 fatcat:svpkoe7hjbdv5ki7r3ov3glj2i

Memristors: Devices, Models, and Applications [Scanning the Issue]

Pinaki Mazumder, Sung Mo Kang, Rainer Waser
2012 Proceedings of the IEEE  
Ebong for his assistance in searching the database of memristor papers, cataloging the applications of memristors, and writing the last section of this article. published  ...  Experimentally, STDP has been shown to be viable for a-Si memristor [74] as well as a Cu 2 O device [79] . Larger applications based on spiking neural networks have also been proposed.  ...  Memristors have also been proposed in designing cellular neural networks (CNNs) [60] , [61] , recurrent neural networks [62] , ultrawideband receivers [63] , adaptive filters [64] , oscillators [  ... 
doi:10.1109/jproc.2012.2190812 fatcat:n7ux4tc64bd6bcncqovjq3igli

Research Progress of Biomimetic Memristor Flexible Synapse

Huiling Zhang, Ruping Liu, Huiqing Zhao, Zhicheng Sun, Zilong Liu, Liang He, Ye Li
2021 Coatings  
The use of a flexible memristor to simulate nerve synapses will provide new methods for neural network computing and bionic sensing systems.  ...  The progress of integrated circuit and micro-processing manufacturing technology has greatly promoted development of the flexible memristor.  ...  Although the neural network can bear a certain degree of error, variability and uniformity are still very important for high recognition accuracy of the neural network.  ... 
doi:10.3390/coatings12010021 fatcat:4eqc7amr2fb6xmgtmn3bota3mq

Long-term memory and synapse-like dynamics of ionic carriers in two-dimensional nanofluidic channels [article]

P. Robin
2022 arXiv   pre-print
Our study unveils two types of ionic memristor responses, depending on the type of channel material and confinement, with long-term memory -- from minutes to hours.  ...  ) or ∆V = 0 and |∆V | = V 0 (for unipolar memristors).  ...  This mechanism is independent of voltage sign, and thus does correspond to a self-touching loop in the IV curve, defining what is sometimes called a unipolar memristor.  ... 
arXiv:2205.07653v1 fatcat:kendedtvbrd7ja6bax7nt2q2ka

Ferroelectric tunnel junctions [article]

Vincent Garcia
2020 arXiv   pre-print
Such ferroelectric memristors can be used as artificial synapses in neuromorphic architectures.  ...  spiking neural networks.  ...  learning in spiking neural networks with ferroelectric synapses.  ... 
arXiv:2011.07864v1 fatcat:c3ucz4npprhpblu6ndpohp7naq
« Previous Showing results 1 — 15 out of 38 results