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

[41] An alternative approach to neural network training based on hybrid bio meta-heuristic algorithm
Khan, Abdullah
Shah, Rahmat
Imran, Muhammad
Khan, Asfandyar
Bangash, Javed Iqbal
Shah, Khalid
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2019, 10 (10) : 3821 - 3830
[42] A Hybrid Approach of Spotted Hyena Optimization Integrated with Quadratic Approximation for Training Wavelet Neural Network
Panda, Nibedan
Majhi, Santosh Kumar
Pradhan, Rosy
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2022, 47 (08) : 10347 - 10363
[43] A hybrid neural network training approach of Backpropagation and Genetic Algorithm for classification of remotely sensed images
Chen, YW
Zeng, XY
Nakao, Z
ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 1402 - 1405
[44] The systematic trajectory search algorithm for feedforward neural network training
Tseng, Lin-Yu
Chen, Wen-Ching
2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 1174 - 1179
[45] A hybrid neural network approach for credit scoring
Chuang, Chun-Ling
Huang, Szu-Teng
EXPERT SYSTEMS, 2011, 28 (02) : 185 - 196
[46] TRAINING ELMAN NEURAL NETWORK FOR DYNAMICAL SYSTEM IDENTIFICATION USING STOCHASTIC DYNAMIC BATCH LOCAL SEARCH ALGORITHM
Zhang, Zhiqiang
Tang, Zheng
Gao, Shangce
Yang, Gang
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2010, 6 (04): : 1883 - 1892
[47] Enhancing Network by Reinforcement Learning and Neural Confined Local Search
Hu, Qifu
Li, Ruyang
Deng, Qi
Zhao, Yaqian
Li, Rengang
PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 2122 - 2132
[48] A local search/constraint propagation hybrid for a network routing problem
Lever, J
INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2005, 14 (1-2) : 43 - 60
[49] NOVEL MLP NEURAL NETWORK WITH HYBRID TABU SEARCH ALGORITHM
Peyghami, M. Reza
Khanduzi, R.
NEURAL NETWORK WORLD, 2013, 23 (03) : 255 - 270
[50] Quantized Adversarial Training: An Iterative Quantized Local Search Approach
Guo, Yifan
Ji, Tianxi
Wang, Qianlong
Yu, Lixing
Li, Pan
2019 19TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2019), 2019, : 1066 - 1071

← 1 2 3 4 5 →