The Adaptive Kernel Neural Network

Abstract

A neural network architecture for clustering and classification is described. The Adaptive Kernel Neural Network (AKNN) is a density estimation technique closely related to kernel estimation. The accompanying learning scheme adjusts the connection weights, activation functions, and the number of nodes in the network. The network, as described here, is made up of three layers of nodes: the input layer, a kernel layer and the output, or classification layer. The AKNN retains the inherent parallelism common in neural network models. Its relationship to the kernel estimator allows the network to be understood statistically, and meaningful analysis of the internal representations and the outputs is possible. Keywords: Pattern recognition; Learning; Artificial intelligence; Neural networks; Density estimation; Kernal estimator; Mixture model.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1989
Accession Number
ADA217230

Entities

People

  • C. E. Priebe
  • D. J. Marchette

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Classification
  • Computing System Architectures
  • Data Science
  • Data Sets
  • Estimators
  • Information Science
  • Learning
  • Network Architecture
  • Neural Networks
  • Pattern Recognition
  • Probability
  • Probability Density Functions
  • Statistical Algorithms
  • Statistical Analysis

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks