Re: unboxed structure fields (or class slots)
"Yuri Davidovsky (as work at disclosure dot ie)" <[email protected]>
| Newsgroups | gmane.lisp.lispworks.general |
|---|---|
| Message-ID | <[email protected]> |
> On 14 Jan 2026, at 23:05, David McClain <[email protected]> wrote: > > Frankly, back propagation training seems like the weakest approach you could devise. Absolutely. This is essentially brute forcing interlayer weights into such configuration of the network so that it will (hopefully) place an input in the correct hyperdimensional cluster during inference. > But we don’t know how else to deterministically train a recognition network to recognize data regions that we can’t humanly visualize. We do not. _______________________________________________ Lisp Hug - the mailing list for LispWorks users [email protected] http://www.lispworks.com/support/lisp-hug.html