News for hackers. Stuff that matters.
Re:A Connectome-Based Convolutional Network Model of the Dro... by yedawg on Thursday June 14, 2018 @03:33PM (#17314660)
Using recurrent neural nets to map and train ai based on part of the visual connectome of a fly is interesting but lacks scalable experimental feasibility. Every new neuron in the algorithm introduces an exponential amount of complexity to the ai which takes away from it's scalability.

There are no comments on this comment yet.