Mixed Formal Learning: A Path to Transparent Machine Learning

TL;DR

Mixed Formal Learning introduces an architecture combining formal mathematical models with traditional learning to enhance transparency and enable effective low-shot and zero-shot training without losing accuracy.

Contribution

It proposes a novel architecture that integrates formal mathematical representations with machine learning, improving transparency and training efficiency.

Findings

Facilitates transparency by exposing key latent variables.

Enables low-shot and zero-shot learning without sacrificing accuracy.

Uses formal models to improve interpretability and training efficiency.

Abstract

This paper presents Mixed Formal Learning, a new architecture that learns models based on formal mathematical representations of the domain of interest and exposes latent variables. The second element in the architecture learns a particular skill, typically by using traditional prediction or classification mechanisms. Our key findings include that this architecture: (1) Facilitates transparency by exposing key latent variables based on a learned mathematical model; (2) Enables Low Shot and Zero Shot training of machine learning without sacrificing accuracy or recall.