First of all, merry christmas to everyone on devrant.

Second, another interesting paper--this time on pattern classification using piecewise linear functions vs classic spiking neural nets.

Supposedly it was a *six million* percent improvement in computation time, versus the spiking simulation. Thats my five minute overview of the document anyway.

Highly unusual application (hadn't seen it done before now but maybe I'm unfamiliar). Check it out:


  • 7
    Merry Christmas to you too. Thank you for linking and sharing very interesting things every time. It's still hard to wrap my head around it often but very intriguing.
  • 2
    Is there sample code for any of these things?
  • 4
    @AvatarOfKaine Don't see any. Looks to be verifiable if you know how to translate the math into code. For the record, I didn't verify it. I'm juts impressed with the large number, in the same way a moth might be impressed with a forest fire.
  • 1
    @Wisecrack i enjoyed the analogy
Add Comment