Results 11 to 20 of about 602,374 (329)
Graph Embedded Extreme Learning Machine [PDF]
IEEE Transactions on Cybernetics, 2016 In this paper, we propose a novel extension of the Extreme Learning Machine algorithm for Single-hidden Layer Feedforward Neural network training that is able to incorporate Subspace Learning (SL) criteria on the optimization processfollowed for the ...
Iosifidis, Alexandros +2 more
core +6 more sources
Incremental extreme learning machine [PDF]
2018 22nd International Computer Science and Engineering Conference (ICSEC), 2019 This new theory shows that in order to let SLFNs work as universal approximators, one may simply randomly choose input-to-hidden nodes, and then we only need to adjust the output weights linking the hidden layer and the output layer. In such SLFNs implementations, the activation functions for additive nodes can be any bounded nonconstant piecewise ...
Boonnithi Jiramaneepinit +1 more
openaire +3 more sources
Binary/ternary extreme learning machines [PDF]
Neurocomputing, 2015 In this paper, a new hidden layer construction method for Extreme Learning Machines (ELMs) is investigated, aimed at generating a diverse set of weights. The paper proposes two new ELM variants: Binary ELM, with a weight initialization scheme based on { 0 , 1 } -weights; and Ternary ELM, with a weight initialization scheme based on { - 1 , 0 , 1 ...
van Heeswijk, Mark, Miche, Yoan
openaire +2 more sources
Evolutionary Cost-Sensitive Extreme Learning Machine [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2017 Conventional extreme learning machines solve a Moore-Penrose generalized inverse of hidden layer activated matrix and analytically determine the output weights to achieve generalized performance, by assuming the same loss from different types of misclassification. The assumption may not hold in cost-sensitive recognition tasks, such as face recognition
Lei Zhang, David Zhang
openaire +3 more sources
Optimized Extreme Learning Machine
International Journal for Research in Applied Science and Engineering Technology, 2022 Abstract: Extreme Learning Machine (ELM) is a learning method for single-hidden layer feedforward neural network (SLFN) training. The ELM strategy speeds up learning by generating input weights and biases for hidden nodes at random rather than modifying network parameters, making it much faster than the standard gradient-based approach. In this project,
Roshan Kaloni +3 more
openaire +1 more source
SAFA : a semi-asynchronous protocol for fast federated learning with low overhead [PDF]
, 2020 Federated learning (FL) has attracted increasing attention as a promising approach to driving a vast number of end devices with artificial intelligence.
He, Ligang +5 more
core +2 more sources
Haptic identification by ELM-controlled uncertain manipulator [PDF]
, 2017 This paper presents an extreme learning machine (ELM) based control scheme for uncertain robot manipulators to perform haptic identification. ELM is used to compensate for the unknown nonlinearity in the manipulator dynamics.
Cheng, Hong +4 more
core +1 more source
Development and research of a neural network alternate incremental learning algorithm
Компьютерная оптика, 2023 In this paper, the relevance of developing methods and algorithms for neural network incremental learning is shown. Families of incremental learning techniques are presented. A possibility of using the extreme learning machine for incremental learning is
A.A. Orlov, E.S. Abramova
doaj +1 more source
Hybrid prediction method for solar photovoltaic power generation using normal cloud parrot optimization algorithm integrated with extreme learning machine. [PDF]
Sci RepLiu H +8 more
europepmc +2 more sources
Research on an improved lp-RWMKE-ELM fault diagnosis model
工程科学学报, 2022 As the service time of military equipment increases, equipment failure data is continuously accumulated during events such as routine maintenance, training, and combat readiness exercises, and the data presented is often imbalanced to varying degrees and
Xing LIU +3 more
doaj +1 more source