Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Detection of Gross Error: The Q Test

Detection of Gross Error: The Q Test

When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...

Classification of Systems-II

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,

Classification of Systems-I

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Host transcriptional signatures associated with disease tolerance and environmental persistence in a mosquito-microsporidian system.

Communications biology·2026

Same author

Twelve years of genomic surveillance of vancomycin-resistant Enterococcus faecium: emergence of linear vanA and bacteriocin-carrying plasmids challenging infection control.

Genome medicine·2026

Same author

Authors' Reply to 'Methodological Considerations for Surveys of Dental Students' Knowledge and Attitudes Towards Artificial Intelligence in Oral Cancer Diagnosis'.

Oral diseases·2026

Same author

Knowledge, Attitudes, and Perceptions of Evidence-Based Dentistry Among Final-Year Dental Students: A Multinational Study Across 6 Countries and 8 Universities.

European journal of dental education : official journal of the Association for Dental Education in Europe·2026

Same author

Testing the redox theory of aging under parasitism.

npj aging·2026

Same author

Integrating the Microbiome Into Infection Ecology and Evolution in Wild Animals.

Molecular ecology·2026

Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Search research articles

Related Experiment Videos

Data classification with multilayer perceptrons using a generalized error function.

Luís M Silva¹, J Marques de Sá, Luís A Alexandre

¹INEB-Instituto de Engenharia Biomédica, Porto, Portugal. Imsilva@fe.up.pt

Neural Networks : the Official Journal of the International Neural Network Society

|June 24, 2008

Summary

This summary is machine-generated.

A new generalized error function, E(Exp), for multilayer perceptron learning optimizes performance by emulating other error functions through parameter adjustment. This flexible approach improves results in data classification tasks.

Related Experiment Videos

Area of Science:

Machine Learning
Artificial Intelligence
Neural Networks

Background:

Multilayer perceptron (MLP) learning relies on optimizing error functions to minimize the difference between predicted and target outputs.
Existing error functions possess distinct mathematical properties influencing their effectiveness in data classification.

Purpose of the Study:

To introduce and analyze a novel, generalized error function, E(Exp), for MLP networks.
To demonstrate E(Exp)'s ability to emulate various existing error functions via parameter tuning.
To evaluate E(Exp)'s performance and flexibility in data classification tasks.

Main Methods:

Review and mathematical analysis of common MLP error functions.
Introduction of the E(Exp) error function, inspired by the Z-EDM algorithm.
Experimental evaluation of E(Exp) against traditional error functions on classification problems.

Main Results:

The proposed E(Exp) function exhibits a generalized behavior, capable of mimicking other error functions.
Adjusting a single parameter in E(Exp) allows for emulation of diverse error function characteristics.
Experimental results indicate that E(Exp) achieves optimal performance comparable to specialized functions, with performance improvements in certain cases.

Conclusions:

The E(Exp) error function offers enhanced flexibility and adaptability for MLP training.
Its generalized nature simplifies the selection of appropriate error functions for classification.
E(Exp) represents a significant advancement in optimizing neural network learning processes.