A fundamental challenge in neuroscience is to estimate the structure of white matter connectivity inthehuman brainorconnectomes [14,29]. Connectomes aremadeupofneuronal axonbundles wrapped with myelin sheaths, called fascicles, and connect different areas ofthe brain.

Neural Information Processing Systems http://nips.cc/

We demonstrate the algorithm's effectiveness

Despite their promising performance, the learned knowledge remains implicit in these black-box neural structures, which hinders understanding the importance of input features and how they influencedecisions.

Inhuman principal--agent problems, seemingly inconsequential changes toanagent'sincentives often lead to surprising, counter-intuitive, and counter-productive behavior (21). Consequently, we must ask when thismisalignment is costly: when is it counter-productive to optimize for an incompleteproxy?