The hidden layer design of the MVQ neural network

被引：0

作者：

Abouali, AH ^{[1
]}

Porter, WA ^{[1
]}

机构：

[1] Egyptian Res Ctr, Cairo 11435, Egypt

来源：

THIRTIETH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY (SSST) | 1998年

关键词：

D O I：

10.1109/SSST.1998.660103

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this study, we introduce the first part of neural network classifiers design methodology. The design has a lot of the desired features. The design is based on a preprocessing stage of multiple class vector quantization, MVQ, algorithm. The algorithm extracts the information from the training set. The outcome of this stage fully defines the first hidden layer of the network. The methodology not only has better performance but also provides insights to why and how the neural network works.

引用

下载

页码：393 / 396

页数：4

共 50 条

[21] Factorized Hidden Layer Adaptation for Deep Neural Network Based Acoustic Modeling
Samarakoon, Lahiru
Sim, Khe Chai
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2016, 24 (12) : 2241 - 2250
[22] Wind energy prediction using a two-hidden layer neural network
Grassi, Giuseppe
Vecchio, Pietro
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION, 2010, 15 (09) : 2262 - 2266
[23] Spurious valleys in one-hidden-layer neural network optimization landscapes
Venturi, Luca
Bandeira, Afonso S.
Bruna, Joan
Journal of Machine Learning Research, 2019, 20
[24] Simultaneous Approximation Algorithm Using a Feedforward Neural Network with a Single Hidden Layer
Hahm, Nahmwoo
Hong, Bum Il
JOURNAL OF THE KOREAN PHYSICAL SOCIETY, 2009, 54 (06) : 2219 - 2224
[25] Layered neural network training with model switching and hidden layer feature regularization
Kameyama, K
Taga, K
PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 2294 - 2299
[26] Extending hidden-layer backpropagation neural network and its' training algorithm
School of Computer and Communication Engineering, China University of Petroleum, Dongying 257061, China
不详
Jisuanji Jicheng Zhizao Xitong, 2008, 11 (2284-2288):
[27] Binary Neural Network Classifier and it's Bound for the Number of Hidden Layer Neurons
Chaudhari, Narendra S.
Tiwari, Aruna
11TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV 2010), 2010, : 2012 - 2017
[28] Nuclear mass predictions with multi-hidden-layer feedforward neural network
Le, Xian-Kai
Wang, Nan
Jiang, Xiang
NUCLEAR PHYSICS A, 2023, 1038
[29] Spurious Valleys in One-hidden-layer Neural Network Optimization Landscapes
Venturi, Luca
Bandeira, Afonso S.
Bruna, Joan
JOURNAL OF MACHINE LEARNING RESEARCH, 2019, 20
[30] A new deep neural network based on a stack of single-hidden-layer feedforward neural networks with randomly fixed hidden neurons
Hu, Junying
Zhang, Jiangshe
Zhang, Chunxia
Wang, Juan
NEUROCOMPUTING, 2016, 171 : 63 - 72

← 1 2 3 4 5 →