LGNEJul 16, 2022

Approximation Capabilities of Neural Networks using Morphological Perceptrons and Generalizations

arXiv:2207.07832v12 citationsh-index: 29
Originality Synthesis-oriented
AI Analysis

This work addresses a theoretical limitation for researchers and engineers considering morphological perceptrons in hardware-efficient implementations, showing they are not universally approximating.

The paper demonstrates that max-sum artificial neural networks (ANNs) and their generalizations (signed-max-sum and max-star-sum) lack universal approximation capabilities, in contrast to standard ANNs and log-number system implementations which do.

Standard artificial neural networks (ANNs) use sum-product or multiply-accumulate node operations with a memoryless nonlinear activation. These neural networks are known to have universal function approximation capabilities. Previously proposed morphological perceptrons use max-sum, in place of sum-product, node processing and have promising properties for circuit implementations. In this paper we show that these max-sum ANNs do not have universal approximation capabilities. Furthermore, we consider proposed signed-max-sum and max-star-sum generalizations of morphological ANNs and show that these variants also do not have universal approximation capabilities. We contrast these variations to log-number system (LNS) implementations which also avoid multiplications, but do exhibit universal approximation capabilities.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes