Filters








1,084 Hits in 6.2 sec

On Spiking Neural P Systems and Partially Blind Counter Machines [chapter]

Oscar H. Ibarra, Sara Woodworth, Fang Yu, Andrei Păun
2006 Lecture Notes in Computer Science  
A k-output spiking neural P system (SNP) with output neurons, O 1 ; . . . ; O k , generates a tuple ðn 1 ; . . . ; n k Þ of positive integers if, starting from the initial configuration, there is a sequence  ...  We give characterizations of sets definable by partially blind multicounter machines in terms of k-output SNPs operating in a sequential mode. Slight variations of the models make them universal.  ...  Strongly sequential SNPs and partially blind counter machines We will give a characterization of partially blind multicounter machines.  ... 
doi:10.1007/11839132_10 fatcat:jidod6rxxzd5bblt3u54it45vm

On spiking neural P systems and partially blind counter machines

Oscar H. Ibarra, Sara Woodworth, Fang Yu, Andrei Păun
2007 Natural Computing  
A k-output spiking neural P system (SNP) with output neurons, O 1 ; . . . ; O k , generates a tuple ðn 1 ; . . . ; n k Þ of positive integers if, starting from the initial configuration, there is a sequence  ...  We give characterizations of sets definable by partially blind multicounter machines in terms of k-output SNPs operating in a sequential mode. Slight variations of the models make them universal.  ...  Strongly sequential SNPs and partially blind counter machines We will give a characterization of partially blind multicounter machines.  ... 
doi:10.1007/s11047-007-9043-y fatcat:mo23wockofbrxcvzginkp5vexu

Asynchronous spiking neural P systems

Matteo Cavaliere, Oscar H. Ibarra, Gheorghe Păun, Omer Egecioglu, Mihai Ionescu, Sara Woodworth
2009 Theoretical Computer Science  
However, this problem remains open for the case of standard spiking neural P systems, whose rules can only produce one spike.  ...  We consider here spiking neural P systems with a non-synchronized (i.e., asynchronous) use of rules: in any step, a neuron can apply or not apply its rules which are enabled by the number of spikes it  ...  Moreover, we have given a characterization of a class of spiking neural P systems -the unbounded ones, with µ-halting -in terms of partially blind counter machines.  ... 
doi:10.1016/j.tcs.2009.02.031 fatcat:targwjarungrtbmo2xq2q57yku

Bibliography of spiking neural P systems

Gheorghe Păun
2008 Natural Computing  
What follows is a bibliography of spiking neural P systems (SN P systems, for short), at the level of April 2009.  ...  The list which follows also includes the papers on SN P systems present in the present volume (with the indication "in the present volume"); the papers from the previous proceedings volumes of the Brainstorming  ...  Pȃun: On spiking neural P systems and partially blind counter machines. Proc. UC2006, LNCS 4135, Springer, 2006, 113-129. 29. M. Ionescu, A. Pȃun, Gh. Pȃun, M.J.  ... 
doi:10.1007/s11047-008-9080-1 fatcat:ybyfybe73bgnrh46lbh4wogpb4

On languages generated by asynchronous spiking neural P systems

Xingyi Zhang, Xiangxiang Zeng, Linqiang Pan
2009 Theoretical Computer Science  
Characterizations of finite languages and recursively enumerable languages are obtained by asynchronous spiking neural P systems with extended rules.  ...  The relationships of the languages generated by asynchronous spiking neural P systems with regular and non-semilinear languages are also investigated.  ...  It was shown in [6] that certain classes of sequential SN P systems are equivalent to partially blind counter machines, while others are universal.  ... 
doi:10.1016/j.tcs.2008.12.055 fatcat:wkuzqjyzjzg6hgscwtux7xq3zi

Neuromorphic computing with multi-memristive synapses

Irem Boybat, Manuel Le Gallo, S. R. Nandakumar, Timoleon Moraitis, Thomas Parnell, Tomas Tuma, Bipin Rajendran, Yusuf Leblebici, Abu Sebastian, Evangelos Eleftheriou
2018 Nature Communications  
We focus on phase change memory devices, develop a comprehensive model and demonstrate via simulations the effectiveness of the concept for both spiking and non-spiking neural networks.  ...  The work presents a significant step towards the realization of large-scale and energy-efficient neuromorphic computing systems.  ...  One of the reasons for this inefficiency is that most neural networks are implemented on computing systems based on the conventional von Neumann architecture with separate memory and processing units.  ... 
doi:10.1038/s41467-018-04933-y pmid:29955057 pmcid:PMC6023896 fatcat:ruynadgpsfe77ehyo4onckhjda

Visual neuroprosthesis: a non invasive system for stimulating the cortex

M. Piedade, J. Gerald, L.A. Sousa, G. Tavares, P. Tomas
2005 IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications  
This paper describes a complete visual neuroprosthesis wireless system designed to restore useful visual sense to profoundly blind people.  ...  A prototype of the proposed system was developed and tested.  ...  The scientific discussions and research results obtained contributed significantly to improve this work. A very special acknowledgment is due to Prof. J. Fernandes and to Prof. M.  ... 
doi:10.1109/tcsi.2005.857923 fatcat:pb7tddcbq5fchi3vgkgy6jwzue

Brain–Machine Interface Engineering

Justin C. Sanchez, José C. Principe
2007 Synthesis Lectures on Biomedical Engineering  
The topics featured include analysis techniques for determining neural representation, modeling in motor systems, computing with neural spikes, and hardware implementation of neural interfaces.  ...  Scott Morrison, Shalom Darmanjian, and Greg Cieslewski developed and programmed the first portable systems for online learning of neural data. Later on, our colleagues Dr. Toshi Nishida and Dr.  ...  p(spike = 1,angle) p (angle) (2.3) and p (spike = 0|angle) = 1 -p(spike = 1|angle) .  ... 
doi:10.2200/s00053ed1v01y200710bme017 fatcat:jm6kaqyjurgddmssiru2fy435i

Neural Interfacing: Forging the Human-Machine Connection

Susanne D. Coates
2008 Synthesis Lectures on Biomedical Engineering  
SPIKE IDENTIFICATION USING ANNS Among the many applications for artificial neural networks are pattern recognition ( Fig. 1.16 ) and blind source separation.  ...  For further reading on neural coding consider, "Spikes: Exploring the Neural Code" [12] . EEG: Electroencephalography.  ...  LINKS TO FREE RESOURCES ON THE INTERNET ACKNOWLEDGMENTS I would like to thank the following individuals without whom this book would not have been possible. My wife for her patience and support.  ... 
doi:10.2200/s00148ed1v01y200809bme022 fatcat:sj2w7ygpyfah7bof3lhre5wc2a

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
Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically  ...  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  ...  Acknowledgements Roadmap on Neuromorphic Computing and Engineering This work was partially based on results obtained from a project, JPNP16007, commissioned by the New Energy and Industrial Technology  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4

Dimensions of Neural-symbolic Integration - A Structured Survey [article]

Sebastian Bader, Pascal Hitzler
2005 arXiv   pre-print
Research on integrated neural-symbolic systems has made significant progress in the recent past.  ...  We present a comprehensive survey of the field of neural-symbolic integration, including a new classification of system according to their architectures and abilities.  ...  A front-end (symbolic system) is used to feed symbolic (partial) expert knowledge to a neural or connectionist system which can be trained on raw data, possibly taking the internally represented symbolic  ... 
arXiv:cs/0511042v1 fatcat:wh4bv3oo35akncg3ds6djkws3m

Sponge Examples: Energy-Latency Attacks on Neural Networks [article]

Ilia Shumailov, Yiren Zhao, Daniel Bates, Nicolas Papernot, Robert Mullins, Ross Anderson
2021 arXiv   pre-print
While this enabled us to train large-scale neural networks in datacenters and deploy them on edge devices, the focus so far is on average-case performance.  ...  The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs.  ...  Acknowledgements Partially supported with funds from Bosch-Forschungsstiftung im Stifterverband.  ... 
arXiv:2006.03463v2 fatcat:n7rgs3x3j5e7ljabfxdifpmfpe

Strictly Positive-Definite Spike Train Kernels for Point-Process Divergences

Il Memming Park, Sohan Seth, Murali Rao, José C. Príncipe
2012 Neural Computation  
We explore strictly positive definite kernels on the space of spike trains to offer both a structural representation of this space and a platform for developing statistical measures that explore features  ...  We discuss the properties of both these existing non-strict kernels and the novel strict kernels in terms of their computational complexity, choice of free parameters, and performance on both synthetic  ...  This work was supported by NSF grant ECCS-0856441, and DARPA grant N66001-10-C-2008.  ... 
doi:10.1162/neco_a_00309 pmid:22509968 fatcat:h2vr2fqqgjbkbltheykkahkep4

Deep learning of nanopore sensing signals using a bi-path network [article]

Dario Dematties, Chenyu Wen, Mauricio David Pérez, Dian Zhou, Shi-Li Zhang
2021 arXiv   pre-print
The B-Net performance is evaluated on generated datasets and further applied to experimental data of DNA and protein translocation.  ...  Here, we use deep learning for feature extraction based on a bi-path network (B-Net).  ...  They acknowledge the Graphical Processing Units (GPUs) publicly provided by the Google Collaboratory service for training, validating and evaluating the neural network architecture proposed in  ... 
arXiv:2105.03660v1 fatcat:fyol6rviand5po5j55efe5l7um

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders,  ...  , uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  Acknowledgements Thanks go to Jeremy Sloan and Martin Lotz for internally reviewing this article.  ... 
doi:10.5281/zenodo.4399748 fatcat:63ggmnviczg6vlnqugbnrexsgy
« Previous Showing results 1 — 15 out of 1,084 results