MIXED FORMAL LEARNING A Path to Transparent Machine Learning

被引：0

作者：

Carrico, Sandra ^{[1
]}

机构：

[1] Glynt AI, Mountain View, CA 94043 USA

来源：

2019 13TH IEEE INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING (ICSC) | 2019年

关键词：

component; explainability; transparency; mixed formal learning; machine learning; low shot; zero shot;

D O I：

10.1109/ICSC.2019.00093

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：486 / 488

页数：3