Application of meta-heuristic algorithms for training neural networks and deep learning architectures: A comprehensive review

M Kaveh, MS Mesgari - Neural Processing Letters, 2023 - Springer
The learning process and hyper-parameter optimization of artificial neural networks (ANNs)
and deep learning (DL) architectures is considered one of the most challenging machine …

Metaheuristic design of feedforward neural networks: A review of two decades of research

VK Ojha, A Abraham, V Snášel - Engineering Applications of Artificial …, 2017 - Elsevier
Over the past two decades, the feedforward neural network (FNN) optimization has been a
key interest among the researchers and practitioners of multiple disciplines. The FNN …

Evolutionary design of neural network architectures: a review of three decades of research

HT Ünal, F Başçiftçi - Artificial Intelligence Review, 2022 - Springer
We present a comprehensive review of the evolutionary design of neural network
architectures. This work is motivated by the fact that the success of an Artificial Neural …

River stage prediction based on a distributed support vector regression

CL Wu, KW Chau, YS Li - Journal of hydrology, 2008 - Elsevier
An accurate and timely prediction of river flow flooding can provide time for the authorities to
take pertinent flood protection measures such as evacuation. Various data-derived models …

An evolutionary optimization framework for neural networks and neuromorphic architectures

CD Schuman, JS Plank, A Disney… - … Joint Conference on …, 2016 - ieeexplore.ieee.org
As new neural network and neuromorphic architectures are being developed, new training
methods that operate within the constraints of the new architectures are required …

[HTML][HTML] Comparative analysis of credit card fraud detection in simulated annealing trained artificial neural network and hierarchical temporal memory

EN Osegi, EF Jumbo - Machine Learning with Applications, 2021 - Elsevier
The problem of misclassification has always been a major concern in detecting online credit
card fraud in e-commerce systems. This concern greatly poses a significant challenge to …

Method and apparatus for providing real-time monitoring of an artifical neural network

JD Birdwell, ME Dean, C Schuman - US Patent 10,248,675, 2019 - Google Patents
Primary Examiner—Lut Wong (74) Attorney, Agent, or Firm—Cameron LLP (57) ABSTRACT
A circuit element of a multi-dimensional dynamic adaptive neural network array (DANNA) …

Method and apparatus for constructing a neuroscience-inspired artificial neural network

JD Birdwell, C Schuman - US Patent 9,798,751, 2017 - Google Patents
2014-11-12 Assigned to UNIVERSITY OF TENNESSEE RESEARCH FOUNDATION
reassignment UNIVERSITY OF TENNESSEE RESEARCH FOUNDATION ASSIGNMENT OF …

Mixed H∞/passive synchronization for persistent dwell-time switched neural networks via an activation function dividing method

X Wang, F Li, X Hu, J Wang - Applied Mathematics and Computation, 2023 - Elsevier
The mixed H∞/passive synchronization issue of discrete-time switched neural networks is
studied in this paper. In order to regulate the switching between subsystems, the persistent …

Method and apparatus for constructing, using and reusing components and structures of an artifical neural network

JD Birdwell, ME Dean, C Schuman - US Patent 10,019,470, 2018 - Google Patents
A method and apparatus for constructing a neuroscience-inspired artificial neural network
(NIDA) or a dynamic adaptive neural network array (DANNA) or combinations of …