Harvard University researchers have shown that an important class of artificial intelligence (AI) algorithms could be implemented using chemical reactions.
The researchers note that the machine-learning algorithms, which use a technique called "message passing inference on factor graphs," are a mathematical coupling of ideas from graph theory and probability and already function as critical components of everyday tools. They say that in the long term, these theoretical developments could lead to "smart drugs" that can automatically detect, diagnose, and treat a variety of diseases using a cocktail of chemicals that can perform AI-type reasoning.
"This work shows that it is possible to also build intelligent machines at tiny scales, without needing anything that looks like a regular computer," says Harvard professor Ryan P. Adams.
The research also could produce methods for analyzing natural biological reaction pathways and regulatory networks as mechanisms that are performing statistical inference.
"What makes this project different is that, instead of aiming for general computation, we focused on efficiently translating particular algorithms that have been successful at solving difficult problems in areas like robotics into molecular descriptions," says Harvard professor Nils Napp.
From Harvard University
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found