10,579 Hits in 4.4 sec

A self-organizing short-term dynamical memory network

Callie Federer, Joel Zylberberg
2018 Neural Networks  
The prior work, however, requires precisely constructed synaptic connectivity matrices, without explaining how this would arise in a biological neural network.  ...  We identified a synaptic plasticity mechanism that overcomes this fine-tuning problem, enabling neural networks to learn to form stable representations.  ...  This work was supported by a Canadian Institute for Advanced Research (CIFAR), Azrieli Global Scholar Award, and a Google Faculty Research Award.  ... 
doi:10.1016/j.neunet.2018.06.008 pmid:30007123 fatcat:3kz7fwaonbex7nw6ganmq4d77u

Impact of Synaptic Device Variations on Pattern Recognition Accuracy in a Hardware Neural Network

Sungho Kim, Meehyun Lim, Yeamin Kim, Hee-Dong Kim, Sung-Jin Choi
2018 Scientific Reports  
Interestingly, in neuromorphic systems, the processing and storing of information can be performed simultaneously by modulating the connection strength of a synaptic device (i.e., synaptic weight).  ...  Neuromorphic systems (hardware neural networks) derive inspiration from biological neural systems and are expected to be a computing breakthrough beyond conventional von Neumann architecture.  ...  neural network contribute to the learning process, a precise adjustment of all synaptic weights is necessarily required.  ... 
doi:10.1038/s41598-018-21057-x pmid:29422641 pmcid:PMC5805704 fatcat:a365ghghejfmhk23yi77scqu3u

A New Computational Model for Astrocytes and Their Role in Biologically Realistic Neural Networks

Zahra Sajedinia, Sébastien Hélie
2018 Computational Intelligence and Neuroscience  
In this article, we aim to study the role of astrocytes in synaptic plasticity by exploring whether tripartite synapses are capable of improving the performance of a neural network.  ...  This research provides computational evidence to begin elucidating the possible beneficial role of astrocytes in synaptic plasticity and performance of a neural network.  ...  Some of this work has been presented in the Mathematical and Computational Cognitive Science weekly colloquium in the Department of Psychological Sciences at Purdue University by Zahra Sajedinia.  ... 
doi:10.1155/2018/3689487 pmid:30073021 pmcid:PMC6057343 fatcat:vaqvqskmbfa6zntgjz3aqz6iw4

Beyond Hebb: Exclusive-OR and Biological Learning

Konstantin Klemm, Stefan Bornholdt, Heinz Georg Schuster
2000 Physical Review Letters  
A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied.  ...  Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics.  ...  To summarize, we studied a biologically motivated model for goal-directed learning in multilayer neural networks.  ... 
doi:10.1103/physrevlett.84.3013 pmid:11018999 fatcat:xtzu5mfxsfgrfgcpwz4qzuzivi

A Neuromorphic Architecture for Object Recognition and Motion Anticipation Using Burst-STDP

Andrew Nere, Umberto Olcese, David Balduzzi, Giulio Tononi, Thomas Wennekers
2012 PLoS ONE  
We demonstrate the abilities of our design in a simple environment with distractor objects, multiple objects moving concurrently, and in the presence of noise.  ...  STDP is responsible for the strengthening (or weakening) of synapses in relation to pre-and post-synaptic spike times and has been described as a Hebbian paradigm taking place both in vitro and in vivo  ...  of the biologically inspired neural network.  ... 
doi:10.1371/journal.pone.0036958 pmid:22615855 pmcid:PMC3352850 fatcat:dly775oddnanhl7iwstlyzntvq

Synaptic depression in deep neural networks for speech processing

Wenhao Zhang, Hanyu Li, Minda Yang, Nima Mesgarani
2016 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In addition, we show that when synaptic depression is included in a deep neural network trained for phoneme classification, the performance of the network improves under noisy conditions not included in  ...  We observed that when synaptic depression is added to the hidden layers of a neural network, it reduces the effect of changing background activity in the node activations.  ...  INTRODUCTION One of the major differences between biological neurons and the neuron models used in artificial neural networks is the ability of synaptic weights to change dynamically [1, 2, 3, 4, 5]  ... 
doi:10.1109/icassp.2016.7472802 pmid:28286424 pmcid:PMC5344995 fatcat:pij3dyt6ufb4bdbry4htj7d2ze

Indirect training of a spiking neural network for flight control via spike-timing-dependent synaptic plasticity

Greg Foderaro, Craig Henriquez, Silvia Ferrari
2010 49th IEEE Conference on Decision and Control (CDC)  
Recently, spiking neural networks (SNNs) have been shown capable of approximating the dynamics of biological neuronal networks, and of being trainable by biologicallyplausible learning mechanisms, such  ...  This paper presents a novel indirect training approach to modulate spike-timing-dependent plasticity (STDP) in an action SNN that serves as a flight controller without directly manipulating its weights  ...  Thus, the synaptic weights of NN c , defined as w ij , are directly adjustable, while the synaptic efficacies of NN a can only be modified through a simulated STDP mechanism which is modulated by the input  ... 
doi:10.1109/cdc.2010.5717260 dblp:conf/cdc/FoderaroHF10 fatcat:jscvpkontvenho2etp6icgqngi

Lessons from connectionism in differentiating knowledge types

Stephen Thaler
2014 e-mentor  
synaptic damage occurring within the biological neural networks of the brain.  ...  weights of any neural system, whether synthetic or biological.  ... 
doi:10.15219/em55.1112 fatcat:g6mwdwzkfncmdhbk3bjr4kpxu4

Situation-based memory in spiking neuron-astrocyte network [article]

Susanna Gordleeva, Yuliya A. Tsybina, Mikhail I. Krivonosov, Ivan Y. Tyukin, Victor B. Kazantsev, Alexey A. Zaikin, Alexander N. Gorban
2022 arXiv   pre-print
Our results show that such a system tested on synthesized data with selective astrocyte-induced modulation of neuronal activity provides an enhancement of retrieval quality in comparison to standard spiking  ...  neural networks trained via Hebbian plasticity only.  ...  Acknowledgements The reported study was funded by the Ministry of Science and Higher Education of the Russian Federation (project no. 075-15-2020-808).  ... 
arXiv:2202.07218v1 fatcat:blhnm6ukxnctjmkhka47ipmjni

Phase Change Memtransistive Synapse [article]

Syed Ghazi Sarwat, Benedikt Kersting, Timoleon Moraitis, Vara Prasad Jonnalagadda, Abu Sebastian
2021 arXiv   pre-print
We show that such biomimetic synapses can enable some powerful cognitive frameworks, such as the short-term spike-timing-dependent plasticity (ST-STDP) and stochastic Hopfield neural networks.  ...  In the mammalian nervous system, various synaptic plasticity rules act, either individually or synergistically, and over wide-ranging timescales to dictate the processes that enable learning and memory  ...  Figure 5a shows a bioinspired Hopfield neural network (HNN), comprising phase change memtransistors as synaptic weights.  ... 
arXiv:2105.13861v2 fatcat:7yuz23lfw5egpfn4jng75kzrpe

Noise suppression ability and its mechanism analysis of scale-free spiking neural network under white Gaussian noise

Lei Guo, Enyu Kan, Youxi Wu, Huan Lv, Guizhi Xu, Jun Ma
2020 PLoS ONE  
In this study, the scale-free spiking neural network (SFSNN) is constructed, in which the Izhikevich neuron model is employed as a node, and the synaptic plasticity model including excitatory and inhibitory  ...  SFSNNs with the low ACC. (2) The neural information processing of the SFSNN is the linkage effect of dynamic changes in neuron firing, synaptic weight and topological characteristics. (3) The synaptic  ...  In this study, the SFSNN is a network with dynamic regulation of synaptic weight.  ... 
doi:10.1371/journal.pone.0244683 pmid:33382788 fatcat:w3as6htmtjbbzift3gh4fjdyxy

Analog implementation of pulse-coupled neural networks

Y. Ota, B.M. Wilamowski
1999 IEEE Transactions on Neural Networks  
A computational style described in this article mimics a biological neural network using pulse-stream signaling and analog summation and multiplication.  ...  This paper presents a compact architecture for analog CMOS hardware implementation of voltage-mode pulsecoupled neural networks (PCNN's).  ...  In this scheme both excitatory and inhibitory synaptic weights are controlled, as in natural biological neural networks.  ... 
doi:10.1109/72.761710 pmid:18252551 fatcat:nqpvcxsseze4vjeimbgx537njy

PAX: A mixed hardware/software simulation platform for spiking neural networks

S. Renaud, J. Tomas, N. Lewis, Y. Bornat, A. Daouzli, M. Rudolph, A. Destexhe, S. Saïghi
2010 Neural Networks  
In this paper we present a mixed hardware-software platform, specifically designed for the simulation of spiking neural networks, using conductance-based models of neurons and synaptic connections with  ...  max 300 words) Many hardware-based solutions now exist for the simulation of bio-like neural networks.  ...  Lower plots: synaptic weights of the 36 synapses versus time. A) Uncorrelated input synaptic noise,  = 0. B) Correlation of input synaptic noise,  = 0.8.  ... 
doi:10.1016/j.neunet.2010.02.006 pmid:20434309 fatcat:2dtewzdc3zh3tatompvknggmmq

A hardware friendly unsupervised memristive neural network with weight sharing mechanism

Zhiri Tang, Ruohua Zhu, Peng Lin, Jin He, Hao Wang, Qijun Huang, Sheng Chang, Qiming Ma
2019 Neurocomputing  
A weight sharing mechanism is proposed to bridge the gap of network scale and hardware resource.  ...  Memristive neural networks (MNNs), which use memristors as neurons or synapses, have become a hot research topic recently.  ...  (2042017gf0052 and 2042016kf0189) and the Natural Science Foundation of Hubei Province, China (2017CFB660).  ... 
doi:10.1016/j.neucom.2018.12.049 fatcat:6vbdmdurybcsfb5uty62hxzh5y

From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation

Andrea Soltoggio, Kenneth O. Stanley
2012 Neural Networks  
Citation: SOLTOGGIO, A. and STANLEY, K.O., 2012. From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation. Neural Networks, 34 pp. 28-41.  ...  The neural model learns, memorizes and modifies different behaviors that lead to positive modulation in a variety of settings.  ...  The role of noise This section shows that neural noise is essential to exploring all network states in networks of one neuron to networks of many.  ... 
doi:10.1016/j.neunet.2012.06.005 pmid:22796669 fatcat:zuddmbqbtzf5lgxbl6dtc2lizy
« Previous Showing results 1 — 15 out of 10,579 results