Local search and pseudoinversion: an hybrid approach to neural network training

被引：1

作者：

Rubini, Luca ^{[1
]}

Cancelliere, Rossella ^{[1
]}

Gallinari, Patrick ^{[2
]}

Grosso, Andrea ^{[1
]}

机构：

[1] Univ Turin, Dept Comp Sci, Turin, Italy

[2] Univ Paris 06, Comp Sci Lab, LIP6, Paris, France

来源：

KNOWLEDGE AND INFORMATION SYSTEMS | 2016年 / 48卷 / 02期

关键词：

Neural networks; Random projections; Local search; Pseudoinverse matrix; EXTREME LEARNING-MACHINE; SPECIAL-ISSUE;

D O I：

10.1007/s10115-016-0935-y

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We consider recent successful techniques proposed for neural network training that set randomly the weights from input to hidden layer, while weights from hidden to output layer are analytically determined by Moore-Penrose generalized inverse. This study aimed to analyse the impact on performances when the completely random sampling of the space of input weights is replaced by a local search procedure over a discretized set of weights. The performances of the proposed training methods are assessed through computational experience on several UCI datasets.

引用

页码：493 / 503

页数：11

共 50 条

[31] A novel training algorithm for RBF neural network using a hybrid fuzzy clustering approach
Niros, Antonios D.
Tsekouras, George E.
FUZZY SETS AND SYSTEMS, 2012, 193 : 62 - 84
[32] A Multi-Objective Neural Network for SAR Despeckling based on an Hybrid Training Approach
Vitale, Sergio
Ferraioli, Giampaolo
Pascazio, Vito
Schirinzi, Gilda
2021 7TH ASIA-PACIFIC CONFERENCE ON SYNTHETIC APERTURE RADAR (APSAR), 2021,
[33] A neural network to enhance local search in the permutation flowshop
El-Bouri, A
Balakrishnan, S
Popplewell, N
COMPUTERS & INDUSTRIAL ENGINEERING, 2005, 49 (01) : 182 - 196
[34] Local cluster neural network on-chip training
Zhang, Liang
Sitte, Joaquin
2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, 2006, : 29 - +
[35] Hybrid training of recurrent fuzzy neural network model
Khanesar, Mojtaba Ahmadieh
Shoorehdeli, Mahdi Aliyari
Teshnehlab, Mohammad
2007 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, VOLS I-V, CONFERENCE PROCEEDINGS, 2007, : 2598 - 2603
[36] Hybrid Algorithm for the Optimization of Training Convolutional Neural Network
Albeahdili, Hayder M.
Han, Tony
Islam, Naz E.
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2015, 6 (10) : 79 - 85
[37] Neuroevolution Guided Hybrid Spiking Neural Network Training
Lu, Sen
Sengupta, Abhronil
FRONTIERS IN NEUROSCIENCE, 2022, 16
[38] A Hybrid Approach of Spotted Hyena Optimization Integrated with Quadratic Approximation for Training Wavelet Neural Network
Nibedan Panda
Santosh Kumar Majhi
Rosy Pradhan
Arabian Journal for Science and Engineering, 2022, 47 : 10347 - 10363
[39] An Approach for Heart Disease Detection by Enhancing Training Phase of Neural Network Using Hybrid Algorithm
Rao, B. Srinivasa
SOUVENIR OF THE 2014 IEEE INTERNATIONAL ADVANCE COMPUTING CONFERENCE (IACC), 2014, : 1211 - 1220
[40] An alternative approach to neural network training based on hybrid bio meta-heuristic algorithm
Abdullah Khan
Rahmat Shah
Muhammad Imran
Asfandyar Khan
Javed Iqbal Bangash
Khalid Shah
Journal of Ambient Intelligence and Humanized Computing, 2019, 10 : 3821 - 3830

← 1 2 3 4 5 →