Filters








13,327 Hits in 2.6 sec

Particle Track Reconstruction using Geometric Deep Learning [article]

Yogesh Verma, Satyajit Jena
2020 arXiv   pre-print
We shed some light on the performance, robustness towards noise and double hits, limitations, and application of the proposed algorithm in tracking applications with the possibility to generalize to other  ...  The detector is modeled using the GEANT4 simulation package and EAS is simulated using CORSIKA (COsmic Ray SImulations for KAscade) with a focus on muons originating from EAS.  ...  Acknowledgments The simulation and training works were carried-out in the computing facility in EHEP Lab at IISER Mohali.  ... 
arXiv:2012.08515v2 fatcat:zepposwz3bhrpekhhjh4pkpykq

Subtractive Perceptrons for Learning Images: A Preliminary Report [article]

H.R.Tizhoosh, Shivam Kalra, Shalev Lifshitz, Morteza Babaie
2019 arXiv   pre-print
One factor, however, is clear, namely that the feed-forward structure of current networks is not a realistic abstraction of the human brain.  ...  The path toward strong AI, or Artificial General Intelligence, remains rather obscure.  ...  There currently exists a rather large body of literature on "complex brain networks" [36] , [37] , [6] , [10] . The general idea of using "graphs" in connection with neural networks is not new.  ... 
arXiv:1909.12933v1 fatcat:6em5arhilbay7fbuz5k4yp6lei

Characterizing Self-Developing Biological Neural Networks: A First Step Towards their Application To Computing Systems [article]

Hugues Berry
2005 arXiv   pre-print
In this article, we propose a first model of the structure of biological neural networks.  ...  More importantly, we extract the simple local rules and characteristics governing the growth of such networks, enabling the development of potentially large but realistic biological neural networks, as  ...  Because the model defines the network growth properties, we can now use it to characterize the large neural networks needed for achieving computing tasks.  ... 
arXiv:q-bio/0505021v1 fatcat:7z6k4d7i3nf43jghf5m43w7tn4

Characterizing Self-developing Biological Neural Networks: A First Step Towards Their Application to Computing Systems [chapter]

Hugues Berry, Olivier Temam
2005 Lecture Notes in Computer Science  
In this article, we propose a first model of the structure of biological neural networks.  ...  More importantly, we extract the simple local rules and characteristics governing the growth of such networks, enabling the development of potentially large but realistic biological neural networks, as  ...  Because the model defines the network growth properties, we can now use it to characterize the large neural networks needed for achieving computing tasks.  ... 
doi:10.1007/11494669_38 fatcat:x6gqlpcxufcelgtstvsv3l5sfy

Probabilistic Models and Generative Neural Networks: Towards an Unified Framework for Modeling Normal and Impaired Neurocognitive Functions

Alberto Testolin, Marco Zorzi
2016 Frontiers in Computational Neuroscience  
Though further efforts are required in order to fill the gap between structured Bayesian models and more realistic, biophysical models of neuronal dynamics, we argue that generative neural networks have  ...  This integration allows building more realistic computational models of cognitive functions, which more faithfully reflect the underlying neural mechanisms at the same time providing a useful bridge to  ...  From Toy Models to Realistic, Large-Scale Simulations Finally, the appeal of generative neural networks has long been hindered by their high computational complexity.  ... 
doi:10.3389/fncom.2016.00073 pmid:27468262 pmcid:PMC4943066 fatcat:vlybqbpt4re5dmbc2fsg5c2opu

Accepted Papers

2021 2021 IEEE URUCON  
Measurement Unit Placement Hybrid Model of Artificial Neural Network-Cuckoo Search for Irradiance and Load Forecasting Power Flow and Fault Analysis Using Graph Theory Ferreira, Enrique Formation Control  ...  Hybrid Model of Artificial Neural Network-Cuckoo Search for Irradiance and Load Forecasting Power Flow and Fault Analysis Using Graph Theory Ferraz, Renato An Integer Linear Programming Approach for Phasor  ... 
doi:10.1109/urucon53396.2021.9647111 fatcat:nscnueqsozci3i3znjobyoeeiy

Adaptive self-organization in a realistic neural network model

Christian Meisel, Thilo Gross
2009 Physical Review E  
We show in a realistic model that spike-time-dependent synaptic plasticity can self-organize neural networks robustly toward criticality.  ...  Our model reproduces several empirical observations and makes testable predictions on the distribution of synaptic strength, relating them to the critical state of the network.  ...  Here we address the question whether this mechanism is relevant for real neural networks; we show in a realistic model that synaptic plasticity can self-organize neural networks robustly toward criticality  ... 
doi:10.1103/physreve.80.061917 pmid:20365200 fatcat:zygpbgyyc5c3hd27gvux5gdr6a

Using computational models to relate structural and functional brain connectivity

Jaroslav Hlinka, Stephen Coombes
2012 European Journal of Neuroscience  
We have calculated graph-theoretic measures of functional network topology from numerical simulations of model networks.  ...  The local dynamics for a neural population is taken to be of the Wilson-Cowan type, whilst the structural connectivity patterns used, describing long-range anatomical connections, cover both realistic  ...  Graph-theoretical measures For the purposes of studying functional networks, the graph-theoretic approach is commonly used (Bullmore & Sporns, 2009 ).  ... 
doi:10.1111/j.1460-9568.2012.08081.x pmid:22805059 pmcid:PMC3437497 fatcat:x2flnyrflnex5efe2iizizlahi

Benchmarks for Graph Embedding Evaluation [article]

Palash Goyal, Di Huang, Ankita Goswami, Sujit Rokka Chhetri, Arquimedes Canedo, Emilio Ferrara
2019 arXiv   pre-print
The majority of methods report performance boosts on few selected real graphs. Therefore, it is difficult to generalize these performance improvements to other types of graphs.  ...  We organize the 100 networks in terms of their properties to get a better understanding of the embedding performance of these popular methods.  ...  Neural network approaches The third category of graph embedding approaches is based on neural networks.  ... 
arXiv:1908.06543v3 fatcat:vjy6oule2fau5n2qiez6rw7cxy

Toward a theory of coactivation patterns in excitable neural networks

Arnaud Messé, Marc-Thorsten Hütt, Claus C. Hilgetag, Daniele Marinazzo
2018 PLoS Computational Biology  
One prominent factor shaping FC is the underlying neural network structure. Using a minimalist model of excitation, we investigate how the topology of excitable neural networks contributes to FC.  ...  Using a basic but general model of discrete excitable units that follow a susceptible-excited-refractory activity cycle (SER model), we here analyze how the network activity patterns underlying functional  ...  Indeed, for suitably small graphs, the model even allows the exhaustive characterization of the complete operating range of a particular network architecture.  ... 
doi:10.1371/journal.pcbi.1006084 pmid:29630592 pmcid:PMC5908206 fatcat:mydet5ll3ncgrf3ghmdnu4ryry

Page 4180 of Psychological Abstracts Vol. 86, Issue 10 [page]

1999 Psychological Abstracts  
The model combines mechanisms from oscillator models of the per ception of periodic patterns and neural network models of learning 32489. Glaser, Donald A. & Barch, Davis.  ...  for detecting and characterizing coherent motion in a set Neurocomputing: An International Journal of image frames, using a 2-dimensional sheet of locally connected neural ele- ments.  ... 

On the Temperature of SAT Formulas [chapter]

Jesús Giráldez-Cru, Pedro Almagro-Blanco
2021 Frontiers in Artificial Intelligence and Applications  
In this context, realistic pseudo-industrial random SAT generators have emerged with the aim of reproducing the main features shared by the majority of these application problems.  ...  The PS model is able to control the hardness of the generated formula by introducing some randomizations in the expected structure.  ...  As future work, we plan to extend this analysis with more sophisticated neural networks, including graph neural networks, and other automated ML techniques [13] , and use these regression methods to estimate  ... 
doi:10.3233/faia210115 fatcat:ekkeegannfe3hcvw5jj2z5c54y

Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networks [article]

Xiaochen Zhang, Haitao Zhao, Jun Xiong, Li Zhou, Jibo Wei
2021 arXiv   pre-print
interference graph neural network (HIGNN) to handle these challenges.  ...  First, we characterize diversified link features and interference relations with heterogeneous graphs.  ...  We refer to the proposed framework as heterogeneous inter- Overall performance of the network is usually evaluated by ference graph neural network (HIGNN).  ... 
arXiv:2104.05463v2 fatcat:t4gyp47cyvhzzeemgakz7gecwu

Editorial: Towards an integrated approach to measurement, analysis and modeling of cortical networks

A. Ravishankar Rao, Guillermo A. Cecchi, Ehud Kaplan
2015 Frontiers in Neural Circuits  
Networks Working Group, composed of the following members: John Beggs, Guillermo A.  ...  ACKNOWLEDGMENTS We wish to acknowledge NIMBIOS (National Institute for Mathematical and Biological Synthesis, www.nimbios.org) at the University of Tennessee for providing us support in creating a Cortical  ...  Thus, the second order statistics of the network dynamics depend strongly on the choice of synaptic model, a fact that modelers of neural networks will find very useful.  ... 
doi:10.3389/fncir.2015.00061 pmid:26539082 pmcid:PMC4611055 fatcat:ipe2nzhlejfy7nwu2vheds43im

Understanding principles of integration and segregation using whole-brain computational connectomics: implications for neuropsychiatric disorders

Louis-David Lord, Angus B. Stevner, Gustavo Deco, Morten L. Kringelbach
2017 Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences  
used to study the causal mechanisms of the integration and segregation of information on behaviourally relevant timescales.  ...  We emphasize how novel methods from network science and whole-brain computational modelling can expand beyond traditional neuroimaging paradigms and help to uncover the neurobiological determinants of  ...  We have further demonstrated how generative whole-brain models could be used to investigate neurobiologically realistic mechanisms of disease.  ... 
doi:10.1098/rsta.2016.0283 pmid:28507228 pmcid:PMC5434074 fatcat:ybywypbpevey7fvbiuzuqeceju
« Previous Showing results 1 — 15 out of 13,327 results