Chris McKinstry wrote,
> I think the problem is actually much simpler than most people think,
> because most of the complexity of the brain is involved in fighting the
> second law of thermodynamics.
Doesn't that correspond to saying the problem of space flight is much simpler
than most people think, because most of the complexity of the bird is involved
in fighting the law of gravity (which spacecraft don't need to worry about).
See, the space vehicle first has to get out of Earth's gravity well, and
computer intelligence first has to be organized so that it can self-organize
to oppose the second law of thermodynamics.
> Given the right training data, neural networks
> much simpler than the human brain can actually out perform it (see:
> http://www.wired.com/news/technology/0,1282,31644,00.html)
That article is _two years old_. Whatever became of the "Superhuman Speech
Machine"?
> I expect this
> will be the case with training a neural network with the Mindpixel Corpus.
But I thought the Mindpixel Corpus was ready to rock and roll with a MMPI-2...
Or is that a separate project?
> Aside from that, it's important to get as much data as possible. Nothing
> happens without the data. Which is why nothing interesting has happened in
> AI until the advent of large corpi that have allowed us to make statistical
> attacks on classic problems such as machine translation and speech
> recognition.
So, the human brain, which you say is more complex than necessary, must store
an enormous amount of data so that it can do interesting things. OK, but
doesn't that data need to be organized relationally and systematically? How do
simple algorithms (Self-Organizing Maps and Simple Recurrent Networks) do
that?
Stay hungry,
--J. R.
Useless hypotheses, etc.:
consciousness, phlogiston, philosophy, vitalism, mind, free will, qualia,
analog computing, cultural relativism
Everything that can happen has already happened, not just once,
but an infinite number of times, and will continue to do so forever.
(Everything that can happen = more than anyone can imagine.)
This archive was generated by hypermail 2b30 : Fri Oct 12 2001 - 14:39:41 MDT