Neural-Network and k-Nearest-neighbor Classifiers

Bromley, J. and Sackinger, E. (1991). Neural-Network and k-Nearest-neighbor Classifiers. AT&T Bell Laboratories.

Abstract

The performance of a state-of-the-art neural network classifier for hand-written digits is compared to that of a k-nearest-neighbor classifier and to human performance. The neural network has a clear advantage over the k-nearest-neighbor method, but at the same time does not yet reach human performance. Two methods for combining neural-network ideas and the k-nearest-neighbor algorithm are proposed. Numerical experiments for these methods show an improvement in performance.

Viewing alternatives

Item Actions

Export

You can export this page using these formats

About

• Item ORO ID
• 35666
• Item Type
• Other - Other
• Keywords
• artificial neural networks; neural networks; k-nearest-neighbors; deep learning
• Academic Unit or School
• Faculty of Science, Technology, Engineering and Mathematics (STEM) > Computing and Communications
  Faculty of Science, Technology, Engineering and Mathematics (STEM)
• Copyright Holders
• © 1991 AT&T Bell Laboratories
• Depositing User
• Jane M. Bromley