Filters








261 Hits in 8.6 sec

Journal of Engineering Research and Reports

Zhihui Zhao, Xinyi Lu
2021 Journal of Engineering Research and Reports  
Artificial neural network (ANN) is an algorithmic mathematical model that imitates the behavioral characteristics of animal neural networks for information processing.  ...  It has the advantages of nonlinear, large-scale, and strong parallel processing capabilities, as well as robustness.  ...  In 1984, he proposed the continuous-time Hopfield neural network model, which made pioneering work for the research of neural computers, created a new way for neural networks to be used for associative  ... 
doi:10.9734/jerr/2021/v21i1217506 fatcat:f76iduw7ibdd7mep2y6tujfdde

Generative Models of Brain Dynamics – A review [article]

Mahta Ramezanian Panahi, Germán Abrevaya, Jean-Christophe Gagnon-Audet, Vikram Voleti, Irina Rish, Guillaume Dumas
2021 arXiv   pre-print
By way of conclusion, we present several hybrid generative models from recent literature in scientific machine learning, which can be efficiently deployed to yield interpretable models of neural dynamics  ...  We discuss the limitations and unique dynamical traits of brain data and the complementary need for hypothesis- and data-driven modeling.  ...  Guillaume Dumas is funded by the Institute for Data Valorization (IVADO), Montréal and the Fonds de recherche du Québec (FRQ).  ... 
arXiv:2112.12147v2 fatcat:gg2njt2ks5gudk7ewxype2zvni

A Review of Complex Systems Approaches to Cancer Networks [article]

Abicumaran Uthamacumaran
2020 arXiv   pre-print
Machine learning, network science and algorithmic information dynamics are discussed as current tools for cancer network reconstruction.  ...  Deep Learning architectures and computational fluid models are proposed for better forecasting gene expression patterns in cancer ecosystems.  ...  PyTorch neural networks use backpropagation and gradient descent learning to learn the parameters of the differential equations pertaining to the a priori assumed attractor model that fits the data.  ... 
arXiv:2009.12693v2 fatcat:kt3e4bqaufgwlbhx2wbgzftnpe

A comprehensive review for industrial applicability of artificial neural networks

M.R.G. Meireles, P.E.M. Almeida, M.G. Simoes
2003 IEEE transactions on industrial electronics (1982. Print)  
Index Terms-Architecture, industrial control, neural network (NN) applications, training.  ...  This paper presents a comprehensive review of the industrial applications of artificial neural networks (ANNs), in the last 12 years.  ...  The model consisted of a set of first-order (nonlinear) differentiable equations that minimize a certain energy function [55] .  ... 
doi:10.1109/tie.2003.812470 fatcat:6lhsijh7p5gw7pkhb47xseybki

Adapting machine-learning algorithms to design gene circuits [article]

Tom W Hiscock
2017 bioRxiv   pre-print
Here, we adapt optimization algorithms from machine learning to rapidly screen and design gene circuits capable of performing arbitrary functions.  ...  Our method can be readily applied to biological networks of any type and size, and is provided as an open-source and easy-to-use python module, GeneNet.  ...  by ordinary 420 differential equations.  ... 
doi:10.1101/213587 fatcat:h2siganjzjgv5gn5iveeqnpln4

The KIV model of intentional dynamics and decision making

Robert Kozma, Walter J. Freeman
2009 Neural Networks  
In the K model, meaningful knowledge is repetitiously created and processed in the form of sequences of oscillatory patterns of neural activity distributed across space and time.  ...  Differential equations have a huge variety of types, such as ordinary and partial, linear and nonlinear, deterministic and stochastic.  ...  In this paper, two types of mesoscopic models are described: (i) neuropercolation based on discrete random graph theory; (ii) ordinary differential equations in continuous space-time approach.  ... 
doi:10.1016/j.neunet.2009.03.019 pmid:19395236 fatcat:cix6xatbyfcwpexrzvj4qxa544

Book report

1999 Computers and Mathematics with Applications  
Beyond the classical theory of computational ordinary differential equations (A. Iserles). Numerical analysis of Volterra functional and integral equations (C.T.H. Baker).  ...  An analog VLSI neural network for phase-based machine vision (Bertram E. Shi and Kwok Fai Hui). VI. Speech, handwriting and signal processing.  ... 
doi:10.1016/s0898-1221(98)00257-0 fatcat:q6vnftnmrjgkdbfav74pfyxbwa

A Survey on Analog Models of Computation [article]

Olivier Bournez, Amaury Pouly
2018 arXiv   pre-print
GPAC and Polynomial Ordinary Differential Equations The GPAC, presented in Section 2.2.1, can also be presented in terms of polynomial ordinary differential equations.  ...  The differential semantics describes the evolution of the system by an ordinary differential equation (ODE).  ... 
arXiv:1805.05729v1 fatcat:abb33r5wpbd7tem557fm4vzlqu

Visual Attention Emerges from Recurrent Sparse Reconstruction [article]

Baifeng Shi, Yale Song, Neel Joshi, Trevor Darrell, Xin Wang
2022 arXiv   pre-print
Network layers are represented as ordinary differential equations (ODEs), formulating attention as a recurrent attractor network that equivalently optimizes the sparse reconstruction of input using a dictionary  ...  Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short.  ...  We start from an ordinary differential equation (ODE) description of neural networks and adopt an attractor network (Grossberg & Mingolla, 1987; Zucker et al., 1989; Yen & Finkel, 1998) to describe the  ... 
arXiv:2204.10962v1 fatcat:4ggvodpdgjf5xnrnnhsxcgdjtq

Chaos as an interpretable benchmark for forecasting and data-driven modelling [article]

William Gilpin
2021 arXiv   pre-print
Chaotic systems thus pose a unique challenge to modern statistical learning techniques, while retaining quantifiable mathematical properties that make them controllable and interpretable as benchmarks.  ...  We also exploit the unique generative properties of our dataset in several proof-of-concept experiments: surrogate transfer learning to improve time series classification, importance sampling to accelerate  ...  Acknowledgments and Disclosure of Funding We thank Gautam Reddy, Samantha Petti, Brian Matejek, and Yasa Baig for helpful discussions and comments on the manuscript. W.  ... 
arXiv:2110.05266v1 fatcat:762cndr4a5bzzbfkablmkvbk7u

Artificial Neural Network for Solving Fuzzy Differential Equations under Generalized H – Derivation

Mazin H. Suhhiem
2017 International Journal of Partial Differential Equations and Applications  
The aim of this work is to present a novel approach based on the artificial neural network for finding the numerical solution of first order fuzzy differential equations under generalized H-derivation.  ...  The differentiability concept used in this paper is the generalized differentiability since a fuzzy differential equation under this differentiability can have two solutions.  ...  In recent years artificial neural network (ANN) for estimation of the ordinary differential equation (ODE) and partial differential equation (PDE) has been used.  ... 
doi:10.12691/ijpdea-5-1-1 fatcat:xnabrnxtizdpzdkp34jkuo6wfq

Global exponential stability of neural networks with globally Lipschitz continuous activations and its application to linear variational inequality problem

Xue-Bin Liang, J. Si
2001 IEEE Transactions on Neural Networks  
INTRODUCTION S TABILITY analysis of neural networks has been an important topic in the neural-network field since the Hopfield network model was proposed in [1] and [2] which demonstrated the great potential  ...  For the two applications of Hopfield network, the underlying qualitative property of the network model is the local or global stability of the network equilibrium points.  ...  ACKNOWLEDGMENT The authors would like to thank the Associate Editor and the anonymous reviewers for their helpful comments and suggestions.  ... 
doi:10.1109/72.914529 pmid:18244389 fatcat:gsbsyjftwvcajkyvppawlsv6dm

Verification for Machine Learning, Autonomy, and Neural Networks Survey [article]

Weiming Xiang and Patrick Musau and Ayana A. Wild and Diego Manzanas Lopez and Nathaniel Hamilton and Xiaodong Yang and Joel Rosenfeld and Taylor T. Johnson
2018 arXiv   pre-print
Autonomy in CPS is enabling by recent advances in artificial intelligence (AI) and machine learning (ML) through approaches such as deep neural networks (DNNs), embedded in so-called learning enabled components  ...  This survey presents an overview of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof.  ...  Hybrid automata are state machines where the variables are set by ordinary differential equations. Active Learning allows the learner machine to decide from which data to learn [113] [97] .  ... 
arXiv:1810.01989v1 fatcat:a5ax66lsxbho3fuxuh55ypnm6m

A Rosetta stone for connectionism

J.Doyne Farmer
1990 Physica D : Non-linear phenomena  
The term connectionism is usually applied to neural networks.  ...  Acknowledgements I urge the reader to use these results for peaceful purposes.  ...  For convenience we assume that the soup is well stirred, so that we can model it by a system of ordinary differential equations.  ... 
doi:10.1016/0167-2789(90)90072-w fatcat:g7y3rbzecncqxhufgq6kqh3v4m

Jordan Pi-Sigma Neural Network for Temperature Prediction [chapter]

Noor Aida Husaini, Rozaida Ghazali, Nazri Mohd Nawi, Lokman Hakim Ismail
2011 Communications in Computer and Information Science  
Pi-Sigma Neural Network (PSNN) which lies within this area, is able to maintain the high learning capabilities of HONN.  ...  To overcome such drawbacks in ordinary NN, this research focuses on using a Higher Order Neural Network (HONN).  ...  , 1996) which are a key development in the field of machine learning.  ... 
doi:10.1007/978-3-642-20998-7_61 fatcat:z2xbx55n5rayhnzzuismh7r4ti
« Previous Showing results 1 — 15 out of 261 results