It seems that the ability to learn in flys is genetic. It is effected by several
genes, most notably the CREB gene.<p>Perhaps the current "neuron" model used in neural networks can be made more efficient
if the current neuron model had more long-term information than just a weight.<p>To quote from Martin Brooks "Fly: An Experimental Life" p107:<p>"The linotte gene is not the only gene that works as an on/off
switch in fruit fly learning and memory. The CREB gene, for
instance, seems to work in a similar fashion. It turns on long-term
memory in flies that have received a spaced sequence of training
exercises; turn off or mutate the CREB gene and flies never
acquire a long-term memory, no matter how much training they
receive. But turn it back on again, via a heat-shock promoter,
and the fly's long-term memory potential is miraculously revived.<p>The CREB gene can do more for a fly than simply return its
memory banks to normal, as Tully discovered when he engineered
flies with extra copies. An additional dose of the CREB
gene resulted in flies with photographic memories. The flies no
longer required repeated, spaced, training exercises to acquire
long-term memory. They learned in one lesson what it took
normal flies ten lessons to learn. One simple training exercise
is all it took to make a fruit fly mastermind."<p>It seems to me that if we understood this effect and could construct
artificial neurons that had more than just a weight we might be able
to construct and train neural networks with much less time and effort.<p>Given that the latest efforts involve hundreds of thousands of GPUs,
years of training, and city-level megawatts of power it might make
sense to investigate a "smarter neuron".<p>Artificial genetics for artificial general intelligence?