Intelligence in the brain: A theory of how it works and how to build it

PJ Werbos - Neural Networks, 2009 - Elsevier
This paper presents a theory of how general-purpose learning-based intelligence is
achieved in the mammal brain, and how we can replicate it. It reviews four generations of …

A comprehensive review on RSM-coupled optimization techniques and its applications

A Susaimanickam, P Manickam, AA Joseph - Archives of Computational …, 2023 - Springer
This review article provides a comprehensive analysis of the optimization techniques used
in a wide range of engineering applications. The comparison of various approaches such as …

Neural network for graphs: A contextual constructive approach

A Micheli - IEEE Transactions on Neural Networks, 2009 - ieeexplore.ieee.org
This paper presents a new approach for learning in structured domains (SDs) using a
constructive neural network for graphs (NN4G). The new model allows the extension of the …

Integrating Elman recurrent neural network with particle swarm optimization algorithms for an improved hybrid training of multidisciplinary datasets

MF Ab Aziz, SA Mostafa, CFM Foozy… - Expert Systems with …, 2021 - Elsevier
There are several types of neural networks (NNs) that are widely used for data classification
tasks. The supervised learning NN is an advanced network with a training algorithm for …

Training recurrent neural networks with the Levenberg–Marquardt algorithm for optimal control of a grid-connected converter

X Fu, S Li, M Fairbank, DC Wunsch… - IEEE transactions on …, 2014 - ieeexplore.ieee.org
This paper investigates how to train a recurrent neural network (RNN) using the Levenberg-
Marquardt (LM) algorithm as well as how to implement optimal control of a grid-connected …

Nonlinear model identification and adaptive model predictive control using neural networks

VA Akpan, GD Hassapis - ISA transactions, 2011 - Elsevier
This paper presents two new adaptive model predictive control algorithms, both consisting of
an on-line process identification part and a predictive control part. Both parts are executed at …

Analysis of direct selection in head-mounted display environments

P Lubos, G Bruder, F Steinicke - 2014 IEEE Symposium on 3D …, 2014 - ieeexplore.ieee.org
The design of 3D user interfaces (3DUIs) for immersive head-mounted display (HMD)
environments is an inherently difficult task. The fact that usually haptic feedback is absent …

Goal representation heuristic dynamic programming on maze navigation

Z Ni, H He, J Wen, X Xu - IEEE transactions on neural networks …, 2013 - ieeexplore.ieee.org
Goal representation heuristic dynamic programming (GrHDP) is proposed in this paper to
demonstrate online learning in the Markov decision process. In addition to the (external) …

Novel maximum-margin training algorithms for supervised neural networks

O Ludwig, U Nunes - IEEE Transactions on Neural Networks, 2010 - ieeexplore.ieee.org
This paper proposes three novel training methods, two of them based on the
backpropagation approach and a third one based on information theory for multilayer …

Sparse simultaneous recurrent deep learning for robust facial expression recognition

M Alam, LS Vidyaratne… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Facial expression recognition is a challenging task that involves detection and interpretation
of complex and subtle changes in facial muscles. Recent advances in feed-forward deep …