For example, certain parts of a neural network can be shown to activate in response to specific components of an input image—edges, different types of texture, or faces, for example.

To test the algorithm underlying that approach, Esmail Bonakdarian, Ph.D., an assistant professor of Computing Sciences and Mathematics at Franklin, leveraged the Glenn IBM 1350 Opteron cluster ...

Real world examples have shown that the misuse of algorithms in healthcare could perpetuate human prejudices or inadvertently cause harm when the machines are trained on biased datasets.