Researchers teach computers to reason like humans, solve moral dilemmas

A team of researchers from Northwestern University, led by Professor Ken Forbus, is giving computers the ability to reason more like humans and even make moral decisions. The team’s new model, called the structure-mapping engine (SME), is capable of problem solving using, and can even recreate the way humans spontaneously use analogies between situations to solve moral dilemmas.

“In terms of thinking like humans, analogies are where it’s at,” said Forbus, Walter P. Murphy Professor of Electrical Engineering and Computer Science in Northwestern’s McCormick School of Engineering. “Humans use relational statements fluidly to describe things, solve problems, indicate causality, and weigh moral dilemmas.”

The researchers based their model on the work of psychologist Dedre Gentner, who developed a structure-mapping theory of analogy and similarity, which has been used to explain and predict many psychology phenomena. The theory of structure-mapping states that analogy and similarity involve comparisons between relational representations, which connect entities and ideas, so, for example, it lets you know that there’s a clock is above a door or that pressure differences can cause water to flow.

Previous models of analogy, which include earlier versions of SME, have not been able to scale to the size of representations that people tend to use, but the team’s new version can handle different levels of complexity that are needed for visual reasoning, as well as solving textbook problems and moral dilemmas.

“Relational ability is the key to higher-order cognition,” said Gentner, Alice Gabrielle Twight Professor in Northwestern’s Weinberg College of Arts and Sciences. “Although we share this ability with a few other species, humans greatly exceed other species in ability to represent and reason with relations.”

Other artificial intelligence systems, like Google’s AlphaGo, rely on deep learning, in which a computer learns by examining large amounts of data. Humans, on the other hand, and SME-based systems, are capable of learning from fewer examples.

“Given a new situation, the machine will try to retrieve one of its prior stories, looking for analogous sacred values, and decide accordingly,” said Forbus.

To further this research on analogy, the Northwestern team is releasing the SME source code and a 5,000-example corpus, which includes comparisons drawn from visual problem solving, textbook problem solving, and moral decision making.

Analogy-based artificial intelligence techniques could have future applications in areas such as security, health care, and education.

“SME is already being used in educational software, providing feedback to students by comparing their work with a teacher’s solution,” Forbus said. But there is a vast untapped potential for building software tutors that use analogy to help students learn.”

Story via Northwestern University.