News for hackers. Stuff that matters.
Re:Is There a Smarter Path to Artificial Intelligence? Some ... by chii on Thursday June 21, 2018 @11:11AM (#17365856)
> we start with some priors (random weights)

i dont think we start with random priors. We start with a set of priors that are geared for certain things - facial recognition, language etc. The environment then fine tunes them.

Re:Is There a Smarter Path to Artificial Intelligence? Some ... by garmaine on Friday June 22, 2018 @02:43AM (#17371920)
There is no way that the genome encodes synaptic layouts to such a detail as to specify an algorithmic prior. At best it specifies, loosely, the generic architecture of how many neurons, how many layers, how tightly folded, and where the inputs (senses) connect. We develop the same algorithms because we all start with the same priors in largely the same gestational and early infant environments.
Re:Is There a Smarter Path to Artificial Intelligence? Some ... by username90 on Friday June 22, 2018 @12:26PM (#17375235)
Right, watch this genius horse learn to walk and navigate a 3d environments just hours after birth: https://www.youtube.com/watch?v=RXKdYThau7c

No, we don't "learn" how to balance, how to identify objects and navigate 3d environments. All of that is highly codified in our DNA from hundreds of millions of years of evolution. Human babies, similar to kangaroos, are just born too early for those systems to have developed.

Re:Is There a Smarter Path to Artificial Intelligence? Some ... by garmaine on Friday June 22, 2018 @02:59PM (#17376452)
Is this sarcasm? You do know that babies (human or animal) exercise their muscles and gain body awareness during gestation, right?