Filters








4,528 Hits in 2.9 sec

Revisiting Algorithmic Lateral Inhibition and Accumulative Computation [chapter]

Antonio Fernández-Caballero, María T. López, Miguel A. Fernández, José M. López-Valles
2009 Lecture Notes in Computer Science  
biologically inspired methods called "algorithmic lateral inhibition", a generalization of lateral inhibition anatomical circuits, and "accumulative computation", a working memory related to the temporal  ...  This paper is dedicated to the computational formulations of both methods, which have led to quite efficient solutions of problems related to motion-based computer vision.  ...  projects PII2I09-0069-0994, PII2I09-0071-3947 and PEII09-0054-9581.  ... 
doi:10.1007/978-3-642-02264-7_7 fatcat:3vixstt3afbidpuctdollm4nfq

A historical perspective of algorithmic lateral inhibition and accumulative computation in computer vision

Antonio Fernández-Caballero, María T. López, Enrique J. Carmona, Ana E. Delgado
2011 Neurocomputing  
", a generalization of lateral inhibition anatomical circuits, and "accumulative computation", a working memory related to the temporal evolution of the membrane potential.  ...  The conjecture of the last fifteen years of joint research has been that any bottom-up organization may be made operational using two biologically inspired methods called "algorithmic lateral inhibition  ...  Acknowledgements This work was partially supported by the Spanish Ministerio de Ciencia e Innovació n under Projects TIN2007-67586-C02 and TIN2010-20845-C03, and by the Spanish Junta de Comunidades de  ... 
doi:10.1016/j.neucom.2010.07.028 fatcat:ykzg3fljlzat3n2gws2kl7zntu

A Finite State Machine Approach to Algorithmic Lateral Inhibition for Real-Time Motion Detection †

María López, Aurelio Bermúdez, Francisco Montero, José Sánchez, Antonio Fernández-Caballero
2018 Sensors  
Moreover, the lateral inhibition method and its application to motion detection tasks have been exploited in various computer vision applications [8] .  ...  Moreover, it outperforms implementations of a complete ALI algorithm and a simplified version of the ALI algorithm-named "accumulative computation"-which was run about ten years ago, now reaching real-time  ...  work was partially supported by Spanish Ministerio de Economía, Industria y Competitividad, Agencia Estatal de Investigación (AEI)/European Regional Development Fund (FEDER, UE) under DPI2016-80894-R and  ... 
doi:10.3390/s18051420 pmid:29751584 pmcid:PMC5982089 fatcat:kkwbnfrlhbg45fdvpjuvplj7ku

The Spatial Leaky Competing Accumulator Model

Viktoria Zemliak, W. Joseph MacInnes
2022 Frontiers in Computer Science  
We trained and compared versions of the SLCA with both global and local lateral inhibition with use of a genetic algorithm, and compared their performance in simulating human fixation latency distribution  ...  A global lateral inhibition, as implemented in the original model of Usher and McClelland, is applied to all competing neurons, while a local implementation allows only inhibition of immediate neighbors  ...  ACKNOWLEDGMENTS This research was supported in part through computational resources of HPC facilities at HSE University (Kostenetskiy et al., 2021) .  ... 
doi:10.3389/fcomp.2022.866029 fatcat:aabdwx7u2fdftiwfknhicjsjvu

50 years of artificial intelligence: A neuronal approach

Antonio Fernández-Caballero, José Mira, Gustavo Deco
2008 Neurocomputing  
Acknowledgements We would like to thank all the authors for their highquality contributions, and the reviewers for agreeing to perform the reviews.  ...  The conjecture is that there are two basic mechanisms (lateral inhibition and accumulative computation) for the synthesis of a great part of the SVA processes.  ...  In this paper an artificial neuronal network approach for moving object segmentation which uses accumulative computation and recurrent lateral interaction, called LIAC, is revisited.  ... 
doi:10.1016/j.neucom.2007.11.001 fatcat:oigfqfq6vbfm3g4gakvb4zz33q

Training Deep Spiking Neural Networks Using Backpropagation

Jun Haeng Lee, Tobi Delbruck, Michael Pfeiffer
2016 Frontiers in Neuroscience  
Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation.  ...  Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation.  ...  The strength of the lateral inhibition was −0.4 and −1.0 for each one as in the case of the SNNs with 1 HL.  ... 
doi:10.3389/fnins.2016.00508 pmid:27877107 pmcid:PMC5099523 fatcat:uv2hg62gfbgqpmiy6n7i2mjkwm

Real-time motion detection by lateral inhibition in accumulative computation

Ana E. Delgado, María T. López, Antonio Fernández-Caballero
2010 Engineering applications of artificial intelligence  
In the few last years, the neurally inspired lateral inhibition in accumulative computation (LIAC) method and its application to the motion detection task have been introduced.  ...  Finite state machines constitute the best characterized computational model, whereas artificial neural networks have become a very successful tool for modeling and problem solving.  ...  Projects PII2I09-0069-0994, PII2I09-0071-3947 and PEII09-0054-9581.  ... 
doi:10.1016/j.engappai.2009.08.006 fatcat:q545oajvhffkfizzyxz6obkbc4

Memory-Efficient Random Order Exponentiation Algorithm

Duc-Phong Le, Ali A. Ghorbani
2020 IEEE Access  
This randomized solution will inhibit attacks that allow operations to be distinguished from one acquisition.  ...  The proposed algorithm requires only (m+1) memory registers instead of (m+r), where r > m as recommended in Tunstall's algorithm. Namely, the proposed algorithm saves about half the memory registers.  ...  CONCLUSION In this article, we revisited Tunstall's random order m-ary exponentiation algorithm.  ... 
doi:10.1109/access.2020.3015099 fatcat:rtcznczsynblpldmskr6cq5c7m

Drug Discovery for Mycobacterium tuberculosis Using Structure-Based Computer-Aided Drug Design Approach

Murtala A. Ejalonibu, Segun A. Ogundare, Ahmed A. Elrashedy, Morufat A. Ejalonibu, Monsurat M. Lawal, Ndumiso N. Mhlongo, Hezekiel M. Kumalo
2021 International Journal of Molecular Sciences  
The review features a perspective involving machine learning, artificial intelligence, quantum computing, and CRISPR combination with available computational techniques as a prospective pathway to design  ...  Also, we show an appraisal of available software and databases on computational drug design with an insight into the application of this software and databases in the development of anti-tubercular drugs  ...  Acknowledgments: The authors acknowledge the College of Health Science, University of KwaZulu-Natal, South Africa, and the Centre of High-Performance Computing (CHPC), Cape Town, RSA, for computational  ... 
doi:10.3390/ijms222413259 pmid:34948055 pmcid:PMC8703488 fatcat:wyw2ukfdwrf6rp76agwifbat6a

Review and Modeling of Crystal Growth of Atropisomers from Solutions

Lotfi Derdour, Eric J. Chan, Dimitri Skliar
2019 Processes  
A parameter estimation algorithm was derived to extract those coefficients from data about temporal concentration and crystal size during crystallization and was designed to have a short run time, while  ...  The model predicts a decrease of the growth inhibition effect by the wrong conformer with increasing temperature, likely due to faster equilibration between conformers and/or a decrease of the population  ...  Computation of WC reduced growth inhibition factor in expected ranges for E a , and temperature for A.  ... 
doi:10.3390/pr7090611 fatcat:ptv2kshzdraxlcc4udr6r7ludu

Biologically plausible learning in neural networks with modulatory feedback

W. Shane Grant, James Tanner, Laurent Itti
2017 Neural Networks  
Our results predict that the mechanisms we use are integral for learning modulatory connections in the brain and furthermore that modulatory connections have a strong dependence on inhibition.  ...  We develop a new learning rule designed around the complications of learning modulatory feedback and composed of three simple concepts grounded in physiologically plausible evidence.  ...  Orientation neurons further have lateral connections in a center-surround fashion to promote grouping and competition. Excitation extends to 0.27r, inhibition to 0.73r.  ... 
doi:10.1016/j.neunet.2017.01.007 pmid:28189041 fatcat:nv7duhrwdzhwra7k7zkov7jabm

Local Information with Feedback Perturbation Suffices for Dictionary Learning in Neural Circuits [article]

Tsung-Han Lin
2017 arXiv   pre-print
The resulting network encodes the error signal needed for learning as the change of network steady states caused by feedback, and operates akin to the classical stochastic gradient descent method.  ...  We describe a neural network with spiking neurons that can address the aforementioned fundamental challenge and solve the L1-minimizing dictionary learning problem, representing the first model able to  ...  Acknowledgments The author thanks Peter Tang, Javier Turek, Narayan Srinivasa and Stephen Tarsa for insightful discussion and feedback on the manuscript, and Hong Wang for encouragement and support.  ... 
arXiv:1705.07149v1 fatcat:qs2eycfsubfg3mladqv67hlk2i

Deriving Efficient Graph Algorithms [chapter]

John H. Reif, William L. Scherlis
2003 Lecture Notes in Computer Science  
The algorithms derived are the linear-time depth-first-search algorithms developed by Tarjan and Hopcroft for strong connectivity and biconnectivity.  ...  These algorithms are generally considered by students to be complex and difficult to understand.  ...  This paper is in honor of Zohar Manna, his technical contributions, and his inspiration.  ... 
doi:10.1007/978-3-540-39910-0_28 fatcat:hgo2u2cbj5fy7hr4dncgykvqkm

An adaptive focus-of-attention model for video surveillance and monitoring

James W. Davis, Alexander M. Morison, David D. Woods
2006 Machine Vision and Applications  
We expect that these efficient and effective algorithms are implementable within current commercial camera systems.  ...  The temporal signature of translating objects is extracted using motion history images (MHIs) and an original, efficient algorithm based on an iterative candidacy-classification-reduction process to separate  ...  is revisited.  ... 
doi:10.1007/s00138-006-0047-x fatcat:logpcaxqibbmrmz3hydhtxyf7a

Influence of environmental statistics on inhibition of saccadic return

S. Farrell, C. J. H. Ludwig, L. A. Ellis, I. D. Gilchrist
2009 Proceedings of the National Academy of Sciences of the United States of America  
evidence, and the threshold controlling the amount of evidence needed to generate a saccade. decision-making | computational modeling | saccadic eye movements | reaction time | accumulator models O ur  ...  , a location is unlikely to provide any new information if immediately revisited (e.g., refs. 8, 11, 13, and 15).  ...  , a location is unlikely to provide any new information if immediately revisited (e.g., refs. 8, 11, 13, and 15 ).  ... 
doi:10.1073/pnas.0906845107 pmid:20080778 pmcid:PMC2818969 fatcat:oawplcwm4vgcthc45v5ha5rpdy
« Previous Showing results 1 — 15 out of 4,528 results