New method peeks inside the 'black box' of artificial intelligence

Computer scientists have developed a promising new approach for interpreting machine learning algorithms. Unlike previous efforts, which typically sought to 'break' the algorithms by removing key words from inputs to yield the wrong answer, the researchers instead reduced the inputs to the bare minimum required to yield the correct answer. On average, the researchers got the correct answer with an input of less than three words.

from Latest Science News -- ScienceDaily https://ift.tt/2CQOnql