I think the tooling/scale is at a point where we can begin the search for “life” (eg viruses, boundaries that repair, etc) in weights during training. We should certainly expect to see such things if the NN is found via evolutionary algorithm. So we can look for similar structures in similar places with backprop+SGD. I expect this to go much like the search for life on mars. A negative result would still be good information IMO.
I think the tooling/scale is at a point where we can begin the search for “life” (eg viruses, boundaries that repair, etc) in weights during training. We should certainly expect to see such things if the NN is found via evolutionary algorithm. So we can look for similar structures in similar places with backprop+SGD. I expect this to go much like the search for life on mars. A negative result would still be good information IMO.