Artificial intelligence system uses transparent, human-like reasoning to solve problems

A child is presented with a picture of various shapes and is asked to find the big red circle. To come to the answer, she goes through a few steps of reasoning: First, find all the big things; next, find the big things that are red; and finally, pick out the big red thing that’s a circle.

We learn through reason how to interpret the world. So, too, do neural networks. Now a team of researchers from MIT Lincoln Laboratory’s Intelligence and Decision Technologies Group has developed a neural network that performs human-like reasoning steps to answer questions about the contents of images. Named the Transparency by Design Network (TbD-net), the model visually renders its thoug…
MIT News – Electrical engineering and computer science (EECS) – Computer science and technology

2 Responses

  1. 18/11/2018

    […] sense,” Kulzick said. “Solutions demand timely and accurate information. If I’m going to solve a problem, I’ve got to know what’s actually going on, and to do that I need all of these different […]

  2. 21/02/2019

    […] you sit on a bus in case Google’s Larry Page sits down next to you with a pop quiz? Our handy A.I. buzzword guide is here to […]

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: