Filters








551 Hits in 6.7 sec

The Physics of Intelligence

E. E. Escultura
2012 Journal of Education and Learning  
This paper explores the physics of intelligence and provides an overview of what happens in the brain when a person is engaged in mental activity that we classify under thought or intelligence.  ...  These activity and capability of the CIR are creative. All of it is accomplished through the new methodology of qualitative mathematics and modeling.  ...  Since neural network is a physical entity encoded with vibration characteristics it is ultimately genetically encoded and when the neurons die the encoded information (vibration characteristics) is passed  ... 
doi:10.5539/jel.v1n2p51 fatcat:kaqbznubynb2liltbwwahzovwe

Physics-informed deep-learning applications to experimental fluid mechanics [article]

Hamidreza Eivazi, Ricardo Vinuesa
2022 arXiv   pre-print
Physics-informed deep learning provides frameworks for integrating data and physical laws for learning.  ...  In this study, we apply physics-informed neural networks (PINNs) for super-resolution of flow-field data both in time and space from a limited set of noisy measurements without having any high-resolution  ...  Part of the analysis was carried out using computational resources provided by the Swedish National Infrastructure for Computing (SNIC).  ... 
arXiv:2203.15402v1 fatcat:cdxtr5pazngztjg6x4idxdgnyq

Active flow control using machine learning: A brief review

Feng Ren, Hai-bao Hu, Hui Tang
2020 Journal of Hydrodynamics  
Nowadays the rapidly developing artificial intelligence has become a key solution for problems of diverse disciplines, especially those involving big data.  ...  This article surveys recent successful applications of machine learning in AFC, highlights general ideas, and aims at offering a basic outline for those who are interested in this specific topic.  ...  Acknowledgements This work was support by the Research Grants Council of Hong Kong under General Research Fund (Grant Nos. 15249316, 15214418) , the Departmental General Research Fund (Grant No.  ... 
doi:10.1007/s42241-020-0026-0 fatcat:3iktdc2ihzf6bensgwykli3hxm

A hybrid partitioned deep learning methodology for moving interface and fluid-structure interaction [article]

Rachit Gupta, Rajeev Kumar Jaiman
2021 arXiv   pre-print
We present a hybrid partitioned deep learning framework for the reduced-order modeling of fluid-structure interaction.  ...  The first component of our framework relies on the proper orthogonal decomposition-based recurrent neural network (POD-RNN) as a DL-ROM procedure to infer the point cloud with a moving interface.  ...  Acknowledgement The authors would like to acknowledge the Natural Sciences and Engineering Research Council of Canada (NSERC) for the funding.  ... 
arXiv:2102.09095v2 fatcat:r5s5r4mskzcvrawb42gidu2wmy

Deep Learning for Stability Analysis of a Freely Vibrating Sphere at Moderate Reynolds Number [article]

A. Chizfahm, R. Jaiman
2021 arXiv   pre-print
We develop a nonlinear data-driven coupling for predicting unsteady forces and vortex-induced vibration (VIV) lock-in of the freely vibrating sphere in a transverse direction.  ...  The proposed DL-ROM has the format of a nonlinear state-space model and employs a recurrent neural network with long short-term memory (LSTM).  ...  Two sets of data with different responses are collected for the study. The training data set is used to construct a model, and the validity of the model is determined by how well  ... 
arXiv:2112.09858v1 fatcat:ospssqzlmrcdnmmf77w5sav7z4

A Review on Adaptive Methods for Structural Control

Ilaria Venanzi
2016 Open Civil Engineering Journal  
This paper provides an up-to-date survey on strategies currently available for adaptive control and a literature overview of solutions examined until today for structural applications.  ...  In the last decades, with the diffusion of active and semiactive control applications in civil engineering, adaptive methods started to be adopted for structural control.  ...  Another kind of non-model based controllers are neural networks controllers exploiting artificial neural networks. Their main advantage is the ability to learn on-line with no a priori training.  ... 
doi:10.2174/1874149501610010653 fatcat:6yxvvwk4vzetpamx273zac5fca

Applications of Machine Learning to Wind Engineering

Teng Wu, Reda Snaiki
2022 Frontiers in Built Environment  
high-performance computational hardware, provide an opportunity for the community to embrace and harness full potential of machine learning (ML).  ...  This state-of-the-art review suggests to what extend ML has been utilized in each of these topic areas within wind engineering and provides a comprehensive summary to improve understanding how learning  ...  From Table 5 , it can be concluded that most applications used ML as a regression model for prediction of steady-state force coefficients, flutter derivatives and vortex-induced vibrations (VIV) of various  ... 
doi:10.3389/fbuil.2022.811460 fatcat:4wch33eqgvgx3cbw3agonxfkeq

From Spin Torque Nano-Oscillators to Memristors: Multi-Functional Nanodevices for Advanced Computing [article]

Julie Grollier
2014 arXiv   pre-print
This Habilitation Thesis written in 2013 reviews my research work on spin torque nano-oscillators (from zero-field oscillations, to synchronization and vortex oscillators) and memristive devices (spin  ...  This is the case for cache memories, and for memristor synapses in unsupervised on-line neural networks were learning and adaptation is constant.  ...  For that reason it is a model system for deriving the spin transfer force acting on the non-uniform magnetic vortex.  ... 
arXiv:1407.1494v1 fatcat:3s7qby2ysngifjlxcl55su6nda

Wing Load and Angle of Attack Identification by Integrating Optical Fiber Sensing and Neural Network Approach in Wind Tunnel Test

Daichi Wada, Masato Tamayama
2019 Applied Sciences  
Using this model in a wind tunnel test, we demonstrate load and AoA identification through a neural network approach.  ...  We input the FBG data and the eight flap angles to a neural network and output estimated load distributions on the eight wing segments.  ...  The load distributions were successfully identified, even for data that were not used for training of the neural network. The error range was from −1.5-1.4 N with a standard deviation of 0.57 N.  ... 
doi:10.3390/app9071461 fatcat:5epz7rkbpregjierdublvrqbly

Machine Learning Techniques in Structural Wind Engineering: A State-of-the-Art Review

Karim Mostafa, Ioannis Zisis, Mohamed A. Moustafa
2022 Applied Sciences  
The review demonstrates that the artificial neural network (ANN) is the most powerful tool that is widely used in wind engineering applications, but the paper still identifies other powerful ML models  ...  this field, such as regression trees, random forest, neural networks, etc.  ...  learning algorithm in the recurrent neural network (RNN) face.  ... 
doi:10.3390/app12105232 fatcat:oj5cntnkefdm7izpqtinsduxea

DRLinFluids---An open-source python platform of coupling Deep Reinforcement Learning and OpenFOAM

Qiulei Wang, Lei Yan, Gang Hu, Chao Li, Yiqing Xiao, Hao Xiong, Jean Rabault, Bernd R. Noack
2022 Physics of Fluids  
Here, an agent maximizes a cumulative reward by learning a feedback policy by acting in an environment.  ...  We propose an open-source python platform for applications of Deep Reinforcement Learning (DRL) in fluid mechanics.  ...  recurrent neural network to consider this effect and accelerate the learning process.  ... 
doi:10.1063/5.0103113 fatcat:mw32a52i6fgq5fayknzina6yju

Guided Folding of Life's Proteins in Integrate Cells with Holographic Memory and GM-Biophysical Steering

Dirk K. F. Meijer, Hans J. H. Geesink
2018 Open Journal of Biophysics  
cell, providing a field receptive memory structure that is instrumental in guiding the folding process towards coherently oscillating protein networks that are crucial for cell survival.  ...  In addition, an alternative hypothesis is presented in which each individual cell may store integral 3-D information holographically at the virtual border of a 4-D hypersphere that surrounds each living  ...  This theory finds support in the earlier used computational neural network models, in which integral forward processing of information in a neuronal network, leads to a growing addressable holographic  ... 
doi:10.4236/ojbiphy.2018.83010 fatcat:4ii6hikxpbbd7n3wvxuweyblmi

Quantum Neurobiology

Melanie Swan, Renato P. dos dos Santos, Franke Witte
2022 Quantum Reports  
In this review, we discuss a new generation of bio-inspired quantum technologies in the emerging field of quantum neurobiology and present a novel physics-inspired theory of neural signaling (AdS/Brain  ...  Second are those that develop neural dynamics as a broad approach to quantum neurobiology, consisting of superpositioned data modeling evaluated with quantum probability, neural field theories, filamentary  ...  Quantum formulations are available for the three main machine learning architectures: neural networks [48] , tensor networks [49] , and kernel learning [50] .  ... 
doi:10.3390/quantum4010008 fatcat:jyluuwegufbfdjvucorqy4ifqm

Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution [article]

Omer San, Adil Rasheed, Trond Kvamsdal
2021 arXiv   pre-print
that transfer and represent information between different entities, particularly when different scales are governed by different physics, each operating on a different level of abstraction.  ...  Most modeling approaches lie in either of the two categories: physics-based or data-driven.  ...  ACKNOWLEDGMENTS Conflict of interest The authors declare no potential conflict of interests.  ... 
arXiv:2103.14629v1 fatcat:rwk4ljq4irf6ziam6rc2vw27ra

Journal of Aircraft 2014 Subject Index

2014 Journal of Aircraft  
Neural Networks and Genetic Algorithms C14-024 Importance Measure Method for Rank- ing the Aircraft Component Vulnerability C14-027 Inspection Intervals Optimization for Aircraft Composite Structures Considering  ...  Common Research Model C14-123 Turbulence Model Study for the Flow Around the NASA Common Research Model C14-130 Flow Simulations by Enhanced Implicit Hole-Cutting Method on Overset Grids C14-141 Numerical  ... 
doi:10.2514/1.c033195 fatcat:jvcvdp26efg4bjm3hfa6yuo4mm
« Previous Showing results 1 — 15 out of 551 results