[edbaskerville]

Hey, thanks for writing the original Swarm! Also thought of that immediately when I saw the headline.

I enjoyed using it around 2002, got introduced via Rick Riolo at the the University of Michigan Center for the Study of Complex Systems. It was a bit of a gateway drug for me from software into modeling, particularly since I was already doing OS X/Cocoa stuff in Objective-C.

A lot of scientific modelers start with differential equations, but coming from object-oriented software ABMs made a lot more sense to me, and learning both approaches in parallel was really helpful in thinking about scale, dimensionality, representation, etc. in the modeling process, as ODEs and complex ABMs—often pathologically complex—represent end points of a continuum.

Tangentially, in one of Rick's classes we read about perceptrons, and at one point the conversation turned to, hey, would it be possible to just dump all the text of the Internet into a neural net? And here we are.

[NelsonMinar]

I took a graduate level class in the 1990s from some SFI luminaries. It was a great class but the dismal conclusion was "this stuff is kind of neat but not very practical, traditional optimization techniques usually work better". None of us guessed if you could scale the networks up 1 million X or more they'd become magic.