A Linear Learning Method for Multilayer Perceptrons Using Least-Squares

2007 ◽  
pp. 365-374 ◽  
Author(s):  
Bertha Guijarro-Berdiñas ◽  
Oscar Fontenla-Romero ◽  
Beatriz Pérez-Sánchez ◽  
Paula Fraguela
Keyword(s):  
Least Squares ◽  
Multilayer Perceptrons ◽  
Learning Method

scholarly journals Multilayer Hybrid Deep-Learning Method for Waste Classification and Recycling

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Yinghao Chu ◽  
Chen Huang ◽  
Xiaodan Xie ◽  
Bohai Tan ◽  
Shyam Kamal ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Classification Accuracy ◽  
Image Features ◽  
Learning System ◽  
Multilayer Perceptrons ◽  
Learning Method ◽  
Waste Classification ◽  
Feature Information ◽  
Public Area

This study proposes a multilayer hybrid deep-learning system (MHS) to automatically sort waste disposed of by individuals in the urban public area. This system deploys a high-resolution camera to capture waste image and sensors to detect other useful feature information. The MHS uses a CNN-based algorithm to extract image features and a multilayer perceptrons (MLP) method to consolidate image features and other feature information to classify wastes as recyclable or the others. The MHS is trained and validated against the manually labelled items, achieving overall classification accuracy higher than 90% under two different testing scenarios, which significantly outperforms a reference CNN-based method relying on image-only inputs.

Damage Identification of Structure Based on RBF Neural Network

2013 ◽  
Vol 753-755 ◽  
pp. 2356-2359
Author(s):  
Cheng Gang Zhen ◽  
Xiang Ting Chong
Keyword(s):  
Neural Network ◽  
Least Squares ◽  
Health Monitoring ◽  
Damage Identification ◽  
Rbf Neural Network ◽  
High Accuracy ◽  
Learning Method ◽  
Test Results ◽  
Health Monitoring System ◽  
Orthogonal Least Squares

Health monitoring of the structure is a topic widely concerned and researched in the fields of technology and engineering at home and abroad. Damage identification of structure is an important aspect of the whole health monitoring system. In this paper, the RBF neural network with the effect of bionic is used to the extent, location and area recognition of the damage on the structure with single damage. The method of orthogonal least squares (OLS) is used as the learning method of the network. The test results show that the RBF neural network and the learning method of OLS can identify the damage status of the structure quickly and effectively with high accuracy.

scholarly journals A Fast Learning Method for Multilayer Perceptrons in Automatic Speech Recognition Systems

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Chenghao Cai ◽  
Yanyan Xu ◽  
Dengfeng Ke ◽  
Kaile Su
Keyword(s):  
Speech Recognition ◽  
Training Data ◽  
Cross Entropy ◽  
Multilayer Perceptrons ◽  
Learning Method ◽  
Continuous Speech Recognition ◽  
Dynamic Learning ◽  
Entropy Loss ◽  
Fast Learning ◽  
The Cross

We propose a fast learning method for multilayer perceptrons (MLPs) on large vocabulary continuous speech recognition (LVCSR) tasks. A preadjusting strategy based on separation of training data and dynamic learning-rate with a cosine function is used to increase the accuracy of a stochastic initial MLP. Weight matrices of the preadjusted MLP are restructured by a method based on singular value decomposition (SVD), reducing the dimensionality of the MLP. A back propagation (BP) algorithm that fits the unfolded weight matrices is used to train the restructured MLP, reducing the time complexity of the learning process. Experimental results indicate that on LVCSR tasks, in comparison with the conventional learning method, this fast learning method can achieve a speedup of around 2.0 times with improvement on both the cross entropy loss and the frame accuracy. Moreover, it can achieve a speedup of approximately 3.5 times with only a little loss of the cross entropy loss and the frame accuracy. Since this method consumes less time and space than the conventional method, it is more suitable for robots which have limitations on hardware.

How to Train Multilayer Perceptrons Efficiently With Large Data Sets

2011 ◽  
pp. 186-206
Author(s):  
Hyeyoung Park
Keyword(s):  
Neural Networks ◽  
Computational Cost ◽  
Large Data ◽  
Large Data Sets ◽  
Multilayer Perceptrons ◽  
Data Sets ◽  
Learning Method ◽  
Learning Speed ◽  
Gradient Learning ◽  
On Line Learning

Feed forward neural networks or multilayer perceptrons have been successfully applied to a number of difficult and diverse applications by using the gradient descent learning method known as the error backpropagation algorithm. However, it is known that the backpropagation method is extremely slow in many cases mainly due to plateaus. In data mining, the data set is usually large and the slow learning speed of neural networks is a critical defect. In this chapter, we present an efficient on-line learning method called adaptive natural gradient learning. It can solve the plateau problems, and can be successfully applied to the learning associated with large data sets. We compare the presented method with various popular learning algorithms with the aim of improving the learning speed and discuss briefly the merits and defects of each method so that one can get some guidance as to the choice of the proper method for a given application. In addition, we also give a number of technical tips, which can be easily implemented with low computational cost and can sometimes make a remarkable improvement in the learning speed.

Sign in / Sign up

Export Citation Format

Share Document