An AI methodology to reduce training intensity, error rates, and size of neural networks

TL;DR

This paper introduces a new AI method that reduces training time, errors, and network size for disease diagnosis.

Contribution

A novel neuron model and direct creation algorithm that enable single-iteration convergence and eliminate errors.

Findings

The proposed neuron model can perform both linearly and nonlinearly separable switching functions.

Disease diagnosis examples converge in a single training iteration using the new algorithm.

The method eliminates hallucinations and reduces the need for extensive training.

Abstract

Massive computing systems are required to train neural networks. The prodigious amount of consumed energy makes the creation of AI applications significant polluters. Despite the enormous training effort, neural network error rates limit its use for medical applications, because errors can lead to intolerable morbidity and mortality. Two reasons contribute to the excessive training requirements and high error rates; an iterative reinforcement process (tuning) that does not guarantee convergence and the deployment of neuron models only capable of realizing linearly separable switching functions. tuning procedures require tens of thousands of training iterations. In addition, linearly separable neuron models have severely limited capability; which leads to large neural nets. For seven inputs, the ratio of total possible switching functions to linearly separable switching functions is 41 octillion. Addressed here is the creation of neuron models for the application of disease diagnosis. Algorithms are described that perform direct neuron creation. This results in far fewer training steps than that of current AI systems. The design algorithms result in neurons that do not manufacture errors (hallucinations). The algorithms utilize a template to create neuron models that are capable of performing any type of switching function. The algorithms show that a neuron model capable of performing both linearly and nonlinearly separable switching functions is vastly superior to the neuron models currently being used. Included examples illustrate use of the template for determining disease diagnoses (outputs) from symptoms (inputs). The examples show convergence with a single training iteration.

Figures