Neurodynamical classifiers with low model complexity

DOI10.1016/J.NEUNET.2020.08.013MaRDI QIDQ2057774zbMATH OpenOpenAlexWikidataFDO

Authors Himanshu Pant, Sumit Soman, Amit Bhaya, Basabi Bhaumik Jayadeva

Publication date 7 December 2021

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1503.03148

zbMATH Keywords

classificationlinear programmingneural networkVC-dimensionminimal complexity machine

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: The recently proposed Minimal Complexity Machine (MCM) finds a hyperplane classifier by minimizing an exact bound on the Vapnik-Chervonenkis (VC) dimension. The VC dimension measures the capacity of a learning machine, and a smaller VC dimension leads to improved generalization. On many benchmark datasets, the MCM generalizes better than SVMs and uses far fewer support vectors than the number used by SVMs. In this paper, we describe a neural network based on a linear dynamical system, that converges to the MCM solution. The proposed MCM dynamical system is conducive to an analogue circuit implementation on a chip or simulation using Ordinary Differential Equation (ODE) solvers. Numerical experiments on benchmark datasets from the UCI repository show that the proposed approach is scalable and accurate, as we obtain improved accuracies and fewer number of support vectors (upto 74.3% reduction) with the MCM dynamical system.

Recommendations

• scientific article; zbMATH DE number 6401690
• Sample Complexity of Classifiers Taking Values in ℝ^Q, Application to Multi-Class SVMs
• Estimates of Data Complexity in Neural-Network Learning
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Neural networks with quadratic VC dimension

Cites work

• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 724205 (Why is no real title available?)
• A collective neurodynamic optimization approach to bound-constrained nonconvex optimization
• An efficient simplified neural network for solving linear and quadratic programming problems
• Analysis and design of a recurrent neural network for linear programming
• Control Perspectives on Numerical Algorithms and Matrix Problems
• Dynamical Systems which Solve Optimization Problems with Linear Constraints
• Hamiltonian structure of dynamical systems which solve linear programming problems

Cited in

(4)

• scientific article; zbMATH DE number 1728666 (Why is no real title available?)
• A learning algorithm for the classification of dynamic events using a neuron-like dynamic tree
• An automatic classification pipeline for the complex synaptic structure based on deep learning
• RBF-based neurodynamic nearest neighbor classification in real pattern space

Describes a project that uses

Uses Software

• LIBSVM
• UCI

This page was built for publication: Neurodynamical classifiers with low model complexity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2057774)