MICrONS aims to reduce the gap between the performance of human analysts and that of automated pattern recognition systems, by reverse engineering the algorithms in the brain.

You can read more about it here:

The brain is able to recognize patterns in small amounts of information and learn from them. This ability can be used for a variety of purposes, including recognizing novel patterns that are not distorted or noisy. The brain has been a weakly-informed source of inspiration for machine learning algorithms since the 1940s. However, these algorithms still do not rival the performance of humans.

Source:
https://www.iarpa.gov/research-programs/microns