When neural circuit architecture matters more than synaptic weights: “Weight agnostic neural networks”, Gaier & Ha, 2019 https://arxiv.org/abs/1906.04358
Show this thread
-
I always wondered how instinct was transmitted (by genes? what kinds of genes/proteins). I once heard a very eminent person claim it was done by ALU repeats but that is just silly.
Inspired by precocial species in biology, we set out to search for neural net architectures that can already (sort of) perform various tasks even when they use random weight values.
Article: 
-
-
Yes, a great read on the topic! And there are lots of recent examples that are starting to flesh out details of how specific circuitry (directed by specific genes) mediates specific behavioral instincts
-
Some references for these examples?
- 2 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.