A comparative study of the scalability of a sensitivity-based learning algorithm for artificial neural networks

► Researchers must now study not only accuracy but also scalability. ► Researchers are investigating machine learning scalability to large scale problems. ► The scalability of popular training algorithms for ANNs is analyzed in this research. ► The training algorithm SBLLM performs better than other...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications Vol. 40; no. 10; pp. 3900 - 3905
Main Authors: Peteiro-Barral, Diego, Guijarro-Berdiñas, Bertha, Pérez-Sánchez, Beatriz, Fontenla-Romero, Oscar
Format: Journal Article
Language:English
Published: Amsterdam Elsevier Ltd 01.08.2013
Elsevier
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Artificial neural networks
Biological and medical sciences
Classifier design and evaluation
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Connectionism. Neural networks
Exact sciences and technology
Fundamental and applied biological sciences. Psychology
General aspects
Learning
Linear systems
Machine learning
Mathematical analysis
Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects)
Memory and file management (including protection and security)
Memory organisation. Data processing
Neural nets
Sensitivity analysis
Software
Training
Algorithms
Neural nets
Classifier design and evaluation
Machine learning
Sensitivity analysis
Scalability
Intruder detector
Neural network
Modeling
Optimization
Learning (artificial intelligence)
Classification
Data field
Feedforward
Learning algorithm
Bioinformatics
Artificial intelligence
Computer security
Intrusion detection systems
ISSN:0957-4174, 1873-6793
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:► Researchers must now study not only accuracy but also scalability. ► Researchers are investigating machine learning scalability to large scale problems. ► The scalability of popular training algorithms for ANNs is analyzed in this research. ► The training algorithm SBLLM performs better than others in terms of scalability. ► This research contributes to the standardization of scalability studies. Until recently, the most common criterion in machine learning for evaluating the performance of algorithms was accuracy. However, the unrestrainable growth of the volume of data in recent years in fields such as bioinformatics, intrusion detection or engineering, has raised new challenges in machine learning not simply regarding accuracy but also scalability. In this research, we are concerned with the scalability of one of the most well-known paradigms in machine learning, artificial neural networks (ANNs), particularly with the training algorithm Sensitivity-Based Linear Learning Method (SBLLM). SBLLM is a learning method for two-layer feedforward ANNs based on sensitivity analysis, that calculates the weights by solving a linear system of equations. The results show that the training algorithm SBLLM performs better in terms of scalability than five of the most popular and efficient training algorithms for ANNs.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2012.12.076