A novel double deep ELMs ensemble system for time series forecasting
G Song, Q Dai - Knowledge-Based Systems, 2017 - Elsevier
Abstract Extreme Learning Machine (ELM) has proved to be well suited to different kinds of
classification and regression problems. However, failing to seek deep representation of raw …
classification and regression problems. However, failing to seek deep representation of raw …
Redundant arm kinematic control based on parameterization
S Lee, AK Bejczy - … . 1991 IEEE International Conference on Robotics …, 1991 - computer.org
Neural-network techniques, particularly backpropagation algorithms, have been widely used
as a tool for discovering a map** function between a known set of input and output …
as a tool for discovering a map** function between a known set of input and output …
An improved learning algorithm based on the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method for back propagation neural networks
The Broyden-Fletcher-Goldfarh-Shanno (BFGS) optimization algorithm usually used for
nonlinear least squares is presented and is combined with the modified back propagation …
nonlinear least squares is presented and is combined with the modified back propagation …
[PDF][PDF] A survey on algorithms for training artificial neural networks
Literature review corroborates that artificial neural networks are being successfully applied
in a variety of regression and classification problems. Due of their ability to exploit the …
in a variety of regression and classification problems. Due of their ability to exploit the …
Self-scaled conjugate gradient training algorithms
AE Kostopoulos, TN Grapsa - Neurocomputing, 2009 - Elsevier
This article presents some efficient training algorithms, based on conjugate gradient
optimization methods. In addition to the existing conjugate gradient training algorithms, we …
optimization methods. In addition to the existing conjugate gradient training algorithms, we …
EnsPKDE&IncLKDE: a hybrid time series prediction algorithm integrating dynamic ensemble pruning, incremental learning, and kernel density estimation
G Zhu, Q Dai - Applied Intelligence, 2021 - Springer
Ensemble pruning can effectively overcome several shortcomings of the classical ensemble
learning paradigm, such as the relatively high time and space complexity. However, each …
learning paradigm, such as the relatively high time and space complexity. However, each …
Adaptive control of a two-link flexible manipulator using a type-2 neural fuzzy system
This paper presents a simple novel intelligent control scheme. The devised control scheme
is a Takagi Sugeno Kang (TSK)-based type-2 neural fuzzy system (NFS) with a self-tuning …
is a Takagi Sugeno Kang (TSK)-based type-2 neural fuzzy system (NFS) with a self-tuning …
An improved spectral conjugate gradient neural network training algorithm
IE Livieris, P Pintelas - International Journal on Artificial Intelligence …, 2012 - World Scientific
Conjugate gradient methods constitute excellent neural network training methods which are
characterized by their simplicity and their very low memory requirements. In this paper, we …
characterized by their simplicity and their very low memory requirements. In this paper, we …
Water quality monitoring at a virtual watershed monitoring station using a modified deep extreme learning machine
J **, P Jiang, L Li, H Xu, G Lin - Hydrological Sciences Journal, 2020 - Taylor & Francis
ABSTRACT A new deep extreme learning machine (ELM) model is developed to predict
water temperature and conductivity at a virtual monitoring station. Based on previous …
water temperature and conductivity at a virtual monitoring station. Based on previous …
Adaptive nonmonotone conjugate gradient training algorithm for recurrent neural networks
Recurrent networks constitute an elegant way of increasing the capacity of feedforward
networks to deal with complex data in the form of sequences of vectors. They are well known …
networks to deal with complex data in the form of sequences of vectors. They are well known …