Filters








6,438 Hits in 4.3 sec

Improving pattern retrieval in an auto-associative neural network of spiking neurons

Russell Hunter, Bruce P Graham, Stuart Cobb
2009 BMC Neuroscience  
We investigate whether biologically plausible implementations of these transforms can be found in order to improve the performance of pattern recall in the spiking network.  ...  Introduction Similarities between neural network models of associative memory and the mammalian hippocampus have been examined [1, 2] .  ... 
doi:10.1186/1471-2202-10-s1-p173 fatcat:xct5qtpnkzbpva2aktfd47d53a

LEARNING STIMULUS-STIMULUS ASSOCIATION IN SPATIO-TEMPORAL NEURAL NETWORKS

N. Yusoff, F. Kabir Ahmad, N. ChePa, A. Ab Aziz
2015 Jurnal Teknologi  
We propose a stimulus-stimulus association learning by coupling firing rate and precise spike timing encoding for spatio-temporal neural networks.  ...  We simulate a generic recurrent network with random and sparse connectivity consisting of Izhikevich spiking neurons.  ...  neural networks, with Izhikevich's spiking neurons.  ... 
doi:10.11113/jt.v77.6126 fatcat:4j2a7rlwqzdctkybomcitofxvq

A VLSI Spiking Feedback Neural Network with Negative Thresholding and Its Application to Associative Memory

K. SASAKI, T. MORIE, A. IWATA
2006 IEICE transactions on electronics  
An integrate-and-fire-type spiking feedback network is discussed in this paper.  ...  In our spiking neuron model, analog information expressing processing results is given by the relative relation of spike firing.  ...  Simulation of Associative Memory Using Spiking Neural Network Figure 7 shows a block diagram of the spiking feedback neural network circuit, which consists of 36 neurons with symmetric connections and  ... 
doi:10.1093/ietele/e89-c.11.1637 fatcat:a7tpdtsjpvegdbncr3r4ecqv7u

Simultaneous Bearing Fault Recognition and Remaining Useful Life Prediction Using Joint Loss Convolutional Neural Network

Ruonan Liu, Boyuan Yang, Alexander G. Hauptmann
2019 IEEE Transactions on Industrial Informatics  
In this paper, we adopt spatio-temporal memory (STM) model, in which both associative memory and episodic memory are analyzed and emulated, as the reference of our hardware network architecture.  ...  Simulating human brain with hardware has been an attractive project for many years, since memory is one of the fundamental functions of our brains.  ...  In this model, information is hierarchically stored in a structured spiking neural network as shown in Figure 1 .  ... 
doi:10.1109/tii.2019.2915536 fatcat:bguybtqsmnfbnnhg3gxe4eqy34

A Hardware Implementation of SNN-Based Spatio-Temporal Memory Model

Kefei Liu, Xiaoxin Cui, Yi Zhong, Yisong Kuang, Yuan Wang, Huajin Tang, Ru Huang
2019 Frontiers in Neuroscience  
In this paper, we adopt spatio-temporal memory (STM) model, in which both associative memory and episodic memory are analyzed and emulated, as the reference of our hardware network architecture.  ...  Simulating human brain with hardware has been an attractive project for many years, since memory is one of the fundamental functions of our brains.  ...  In this model, information is hierarchically stored in a structured spiking neural network as shown in Figure 1 .  ... 
doi:10.3389/fnins.2019.00835 pmid:31447641 pmcid:PMC6697024 fatcat:5vfzfoicirg5njbujpmh5cp3tq

MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK

Nooraini Yusoff, Farzana Kabir-Ahmad, Mohamad-Farif Jemili
2020 Journal of Information and Communication Technology  
However, most of the studies are based on sigmoidal neural networks in which some dynamic properties of the data are overlooked due to the absence of spatiotemporal encoding functionalities.  ...  Even though some sequential (motion) learning studies have been proposed using spatiotemporal neural networks, as in those sigmoidal neural networks, the approach used is mainly supervised learning.  ...  ACKNOWLEDGEMENT The authors wish to thank the Ministry of Higher Education Malaysia for funding this study under the Fundamental Research Grant Scheme (S/O: 12893).  ... 
doi:10.32890/jict2020.19.2.3 fatcat:sipaaohaubgmdnbxcztmjpdvpa

Learning Anticipation through Priming in Spatio-temporal Neural Networks [chapter]

Nooraini Yusoff, André Grüning
2012 Lecture Notes in Computer Science  
In this paper, we propose a reward-based learning model inspired by the findings from a behavioural study and biologically realistic properties of spatio-temporal neural networks.  ...  The network can be trained to associate a stimulus pair (with an inter-stimulus interval) to a response, as well as to recognise the temporal sequence of the stimulus presentation.  ...  This research has been funded by the Ministry of Higher Education (Malaysia) and partially supported by EPSRC grant EP/I027831/1.  ... 
doi:10.1007/978-3-642-34475-6_21 fatcat:pzqrb7vtcze43derwmx3u6bh2a

Information Recall Using Relative Spike Timing in a Spiking Neural Network

Philip Sterne
2012 Neural Computation  
We present a neural network that is capable of completing and correcting a spiking pattern given only a partial, noisy version.  ...  It operates in continuous time and represents information using the relative timing of individual spikes. The network is capable of correcting and recalling multiple patterns simultaneously.  ...  We would also like to thank Emli-Mari Nel and Keith Vertanen for proof-reading drafts of this paper. The detailed reviewer comments also contributed to a significantly more coherent paper.  ... 
doi:10.1162/neco_a_00306 pmid:22509970 fatcat:7jz553zwbzesdhenprdpyoj4yi

A review on data clustering using spiking neural network (SNN) models

Siti Aisyah Mohamed, Muhaini Othman, Mohd Hafizul Afifi
2019 Indonesian Journal of Electrical Engineering and Computer Science  
The evolution of Artificial Neural Network recently gives researchers an interest to explore deep learning evolved by Spiking Neural Network clustering methods.  ...  Spiking Neural Network (SNN) models captured neuronal behaviour more precisely than a traditional neural network as it contains the theory of time into their functioning model [1].  ...  Recurrent networks architecture taken from [24] In order to investigate neural information processing involved in formation of associative memories or working memory, recurrent spiking neural networks  ... 
doi:10.11591/ijeecs.v15.i3.pp1392-1400 fatcat:r767f32kcva7leu3zk65hv2rxy

Visual attention and object naming in humanoid robots using a bio-inspired spiking neural network

Daniel Hernández García, Samantha Adams, Alex Rast, Thomas Wennekers, Steve Furber, Angelo Cangelosi
2018 Robotics and Autonomous Systems  
via Spike-Timing Dependent Plasticity in a simple system. • Provides a proof-of-concept case for the integration of biologically inspired neural networks with robotics for basic language acquisition.  ...  h i g h l i g h t s • Develop a neuroanatomically grounded spiking neural network for visual attention with a word learning capability. • Demonstrates that a label could be associated with a salient object  ...  Spikes were then generated and sent to the network to simulate an input spike train in the auditory network.  ... 
doi:10.1016/j.robot.2018.02.010 fatcat:2p6kkcvtcjgcva7irudnjmhose

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  ...  To demonstrate this we present a novel neuromorphic model for short-term memory implemented by a two-net spiking neural-astrocytic network.  ...  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

A Spiking Neuron and Population Model Based on the Growth Transform Dynamical System

Ahana Gangopadhyay, Darshit Mehta, Shantanu Chakrabartty
2020 Frontiers in Neuroscience  
In this paper, we use this network to construct a spiking associative memory that uses fewer spikes compared to conventional architectures, while maintaining high recall accuracy at high memory loads.  ...  In neuromorphic engineering, neural populations are generally modeled in a bottom-up manner, where individual neuron models are connected through synapses to form large-scale spiking networks.  ...  This associates the i-th neuron in the network with a vector x i , mapping it onto an abstract metric space R D and essentially providing an alternate geometric representation of the neural network.  ... 
doi:10.3389/fnins.2020.00425 pmid:32477051 pmcid:PMC7235464 fatcat:pjbywryrqvd2zpnmvstf4oeybu

Robust computation with rhythmic spike patterns

E. Paxon Frady, Friedrich T. Sommer
2019 Proceedings of the National Academy of Sciences of the United States of America  
Second, we construct 2 spiking neural networks to approximate the complex algebraic computations in TPAM, a reductionist model with resonate-and-fire neurons and a biologically plausible network of integrate-and-fire  ...  Here, we propose a type of attractor neural network in complex state space and show how it can be leveraged to construct spiking neural networks with robust computational properties through a phase-to-timing  ...  We thank Pentti Kanerva and members of the Redwood Center for valuable feedback.  ... 
doi:10.1073/pnas.1902653116 pmid:31431524 pmcid:PMC6731666 fatcat:urhs462ppzdvnfjijhn7cchdea

Models of distributed associative memory networks in the brain

Friedrich T. Sommer, Thomas Wennekers
2003 Theory in biosciences  
Impacts of nonlocal associative projections in the brain are discussed with respect to the functionality they can explain.  ...  We describe cell assembly models that integrate more neurobiological constraints and review results from simulations of a simple nonlocal associative network formed by a reciprocal topographic projection  ...  In standard associative memories only one memory can be activated at a time. 3 Neurobiologically constrained assemblies Definition of basic computational units Using an artificial neural network architecture-like  ... 
doi:10.1007/s12064-003-0037-8 fatcat:m2qkjyphjbeehcaoh3a2fpnani

Models of Distributed Associative Memory Networks in the Brain

F SOMMER
2003 Theory in biosciences  
Impacts of nonlocal associative projections in the brain are discussed with respect to the functionality they can explain.  ...  We describe cell assembly models that integrate more neurobiological constraints and review results from simulations of a simple nonlocal associative network formed by a reciprocal topographic projection  ...  In standard associative memories only one memory can be activated at a time. 3 Neurobiologically constrained assemblies Definition of basic computational units Using an artificial neural network architecture-like  ... 
doi:10.1078/1431-7613-00074 fatcat:hwdglpfh7fbntjquccoslocgcu
« Previous Showing results 1 — 15 out of 6,438 results