32,592 Hits in 6.1 sec

A Model of Neural Inspiration for Local Accumulative Computation [chapter]

José Mira, Miguel A. Fernández, Maria T. López, Ana E. Delgado, Antonio Fernández-Caballero
2003 Lecture Notes in Computer Science  
This paper explores the computational capacity of a novel local computational model that expands the conventional analogical and logical dynamic neural models, based on the charge and discharge of a capacity  ...  This model is denominated as accumulative computation and is inspired in biological short-term memory mechanisms.  ...  of a novel local computational model that expands the conventional analogical and logical dynamic neural models, based on the charge and discharge of a capacity or in the use of a D flip-flop.  ... 
doi:10.1007/978-3-540-45210-2_39 fatcat:r5tc7rnywrgunb3mfivia7pury


José Manuel Ferrández, José Santos, Ramiro Varela
2018 Natural Computing  
These papers present contributions of bio-inspired techniques as neural computation, swarm optimization, evolutionary algorithms or local search to some complex problems in artificial vision, protein folding  ...  In this paper, the authors consider lateral interaction in accumulative computation (LIAC), the implementation for computer vision of two biologically-inspired methods denominated algorithmic lateral interaction  ... 
doi:10.1007/s11047-018-9717-7 fatcat:5ouk5tjycrf33dcytdn4f7yqey

Lateral interaction in accumulative computation: a model for motion detection

Antonio Fernández-Caballero, José Mira Mira, Ana E. Delgado, Miguel A. Fernández Graciani
2003 Neurocomputing  
This model is based on a series of neuronal models in one layer, namely the local accumulative computation model, the double time scale model and the recurrent lateral interaction model.  ...  In this paper we present a novel model based on neural networks denominated lateral interaction in accumulative computation (LIAC).  ...  Acknowledgements The authors would like to thank the anonymous referees for their very helpful comments that signiÿcantly improved the manuscript.  ... 
doi:10.1016/s0925-2312(02)00571-4 fatcat:vhvbi54sc5hppnx4nigkdl3sfe

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  
cases of accumulated charge in a local memory.  ...  With the aim of attaining the necessary real-time performance, we used a model of the neutrally-inspired accumulative computation (AC) method, a simplified version of the ALI method in which the more time-consuming  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s18051420 pmid:29751584 pmcid:PMC5982089 fatcat:kkwbnfrlhbg45fdvpjuvplj7ku

The Evolution of the Evolving Neuro-Fuzzy Systems: From Expert Systems to Spiking-, Neurogenetic-, and Quantum Inspired [chapter]

Nikola Kasabov
2013 Studies in Fuzziness and Soft Computing  
This chapter follows the development of a class of intelligent information systems called evolving neuro-fuzzy systems (ENFS).  ...  The review includes fuzzy expert systems, fuzzy neuronal networks, evolving connectionist systems, spiking neural networks, neurogenetic systems, and quantum inspired systems, all discussed from the point  ...  I would like to thank Diana Kassabova for helping me with the manuscript and the editors of the volume for their tremendous effort to put together a memorable collection of chapters representing both the  ... 
doi:10.1007/978-3-642-35641-4_41 fatcat:aghg3dtw3feyll2rzhhjljfanq

Efficient Federated Learning with Spike Neural Networks for Traffic Sign Recognition [article]

Kan Xie, Zhe Zhang, Bo Li, Jiawen Kang, Dusit Niyato, Shengli Xie, Yi Wu
2022 arXiv   pre-print
Therefore, we introduce powerful Spike Neural Networks (SNNs) into traffic sign recognition for energy-efficient and fast model training, which is the next generation of neural networks and is practical  ...  However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server  ...  Then, the vehicle computes the gradient change of the local model (Equations ( 8 ) and ( 11 )) based on the loss to update the model weights. 3) The RSU collects the model parameters uploaded by the  ... 
arXiv:2205.14315v1 fatcat:e26a3yhlp5h47ih56mgfaghae4

Real-Time Accumulative Computation Motion Detectors

Antonio Fernández-Caballero, María Teresa López, José Carlos Castillo, Saturnino Maldonado-Bascón
2009 Sensors  
The neurally inspired accumulative computation (AC) method and its application to motion detection have been introduced in the past years.  ...  Indeed, finite state machines constitute the best characterized computational model, whereas artificial neural networks have become a very successful tool for modeling and problem solving.  ...  in the state of accumulated charge in a local memory [11] .  ... 
doi:10.3390/s91210044 pmid:22303161 pmcid:PMC3267209 fatcat:s7duri2aevd5xocqow3pjzl7wu

Brain-Inspired Learning on Neuromorphic Substrates [article]

Friedemann Zenke, Emre O. Neftci
2020 arXiv   pre-print
This article provides a mathematical framework for the design of practical online learning algorithms for neuromorphic substrates.  ...  Specifically, we show a direct connection between Real-Time Recurrent Learning (RTRL), an online algorithm for computing gradients in conventional Recurrent Neural Networks (RNNs), and biologically plausible  ...  emulation of brain-inspired neural networks.  ... 
arXiv:2010.11931v1 fatcat:e7bwgrmynvgmfkuordiqb3zusq

Using haptics to extract object shape from rotational manipulations

Claudius Strub, Florentin Worgotter, Helge Ritter, Yulia Sandamirskaya
2014 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In the present paper, we thus explore whether a biologically inspired model based on dynamic neural fields can offer a route towards a practical algorithm for tactile SLAM.  ...  We demonstrate that our model can accumulate shape information from reasonably short interaction sequences and autonomously build a representation despite significant ambiguity of the tactile data due  ...  This comparison mechanism has been previously used in a neurally-inspired model for coordinate frame transformations [29] .  ... 
doi:10.1109/iros.2014.6942856 dblp:conf/iros/StrubWRS14 fatcat:yxa5wqtqdffbzac76cvsypugse

Brain-Inspired Learning on Neuromorphic Substrates

Friedemann Zenke, Emre O. Neftci
2021 Proceedings of the IEEE  
This article provides a mathematical framework for the design of practical online learning algorithms for neuromorphic substrates.  ...  Specifically, we show a direct connection between real-time recurrent learning (RTRL), an online algorithm for computing gradients in conventional recurrent neural networks (RNNs), and biologically plausible  ...  of brain-inspired neural networks.  ... 
doi:10.1109/jproc.2020.3045625 fatcat:pelkbpbg5jg7pjyvkvtpgrt2su

Pose Estimation and Map Formation with Spiking Neural Networks: towards Neuromorphic SLAM

Raphaela Kreiser, Alpha Renner, Yulia Sandamirskaya, Panin Pienroj
2018 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
In this paper, we investigate the use of ultra low-power, mixed signal analog/digital neuromorphic hardware for implementation of biologically inspired neuronal path integration and map formation for a  ...  for a mobile robot.  ...  For instance, inspired by the navigation system of rats, a competitive biologically-inspired neural SLAM system -RatSLAM -was proposed [11] , [6] .  ... 
doi:10.1109/iros.2018.8594228 dblp:conf/iros/KreiserRSP18 fatcat:tj33u5m4sbh5fd4mo5dlsjm4qi

Simulating mirror-neuron responses using a neural model for visual action recognition

Falk Fleischer, Antonino Casile, Martin A Giese
2008 BMC Neuroscience  
Transfected and endogenous Kv2.1 is now demonstrated to preferentially accumulate within the axon initial segment (AIS) over other neurite processes; 87% of 14 DIV hippocampal neurons show endogenous channel  ...  Photobleach studies indicated individual channels within the cluster perimeter were highly mobile (FRAP tau=10.4+/-4.8 sec), supporting our model that Kv2.1 clusters are formed by the retention of mobile  ...  We present a neurophysiologically inspired model for the visual recognition of hand movements.  ... 
doi:10.1186/1471-2202-9-s1-p112 pmid:19014551 pmcid:PMC2592246 fatcat:p6vju3ritzfhrdxqe7eammlrbu

Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospects [article]

Bing Wei, Yudi Zhao, Kuangrong Hao, Lei Gao
2021 arXiv   pre-print
Through this survey, it will provide a comprehensive reference for research in this direction.  ...  Then, some points of view about the prospects of the visual perception computational models are presented.  ...  [43] proposed a local-global memory neural network (LGMNN) model ,where the local memory helps learn the individual patterns of a patient and the global memory can learn the group information of disease  ... 
arXiv:2109.03391v1 fatcat:xtgda2x6azd2laun45tqfj77gi

Neuromorphic Electronic Systems for Reservoir Computing [article]

Fatemeh Hadaeghi
2020 arXiv   pre-print
This chapter provides a comprehensive survey of the researches and motivations for hardware implementation of reservoir computing (RC) on neuromorphic electronic systems.  ...  Due to its computational efficiency and the fact that training amounts to a simple linear regression, both spiking and non-spiking implementations of reservoir computing on neuromorphic hardware have been  ...  Introduction The term "neuromorphic computing" refers to a variety of brain-inspired computers, architectures, devices, and models that are used in the endeavor to mimic biological neural networks [1]  ... 
arXiv:1908.09572v2 fatcat:cimkbnvyrjc3lhixlyufgmqy3i

A neural path integration mechanism for adaptive vector navigation in autonomous agents

Dennis Goldschmidt, Sakyasingha Dasgupta, Florentin Worgotter, Poramate Manoonpong
2015 2015 International Joint Conference on Neural Networks (IJCNN)  
Input signals from an allothetic compass and odometry are sustained through leaky neural integrator circuits, which are then used to compute the home vector by local excitation-global inhibition interactions  ...  The emergent behavior of the controlled agent does not only show a robust solution for the problem of autonomous agent navigation, but it also reproduces various aspects of animal navigation.  ...  ACKNOWLEDGMENT This research was supported by the Emmy Noether Program (DFG, MA4464/3-1), and the Federal Ministry of Education and Research (BMBF) by a grant to the Bernstein Center for Computational  ... 
doi:10.1109/ijcnn.2015.7280400 dblp:conf/ijcnn/GoldschmidtDWM15 fatcat:7xrpkxtr45g6bkdnxeen2pc74a
« Previous Showing results 1 — 15 out of 32,592 results