I lvery much ike the part in the deep belief network of having real and imaginary data.<div><br /></div><div>I think there are also many opposing forces working in the brain. So maybe we</div><div>can indeed make a complete complex system that is able to compute behavior at</div><div>many levels, from physical behaviors, Cognitive Neuroscience, Neuroscience,</div><div>to physical devices.</div><div><br /></div><div>I think the Human Brain Project is one small step in this direction, but a big step</div><div>for human kind.</div><div><br /></div><div>Best wishes,</div><div>Marco Wiering</div><div>University of Groningen, the Netherlands</div><div>===========</div><div><br /><span>On 27-01-14, <b class="name">Geoffrey Hinton </b> <geoffrey.hinton@gmail.com> wrote:</span><blockquote cite="mid:CAK8NvqqkqMhAPbogXxiE9jqgV+wLO4jFO9SGwrNR1hBsV0sGyg@mail.gmail.com" class="iwcQuote" style="border-left: 1px solid #00F; padding-left: 13px; margin-left: 0;" type="cite"><div class="mimepart text html"><div dir="ltr"><div><div><div>Actually, evolution did invent the time-shared wheel.<br /><br /></div>To go over rough ground it needs to be 6 feet in diameter with very soft suspension. <br /></div>The
way to do this without being too heavy or large is to time-share two
small sections of the rim each connected to the axle by "spokes" (in compression rather than tension) that
can easily change their length. The swapping in and out of the spokes is not as energy efficient as a wheel but it solves the problem of supplying the rim with nutrients. <br /><br /></div>Geoff<br /><br /></div><div class="gmail_extra">
<br /><br /><div class="gmail_quote">On Mon, Jan 27, 2014 at 9:28 AM, Balázs Kégl <span dir="ltr"><<a href="mailto:balazskegl@gmail.com" target="1">balazskegl@gmail.com</a>></span> wrote:<br /><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="im">> While it is at least worth considering whether the arm from fin argument applies to the nervous system, because we don’t understand how the brain works, we can’t really answer the question whether there is some simpler version that would have worked just as well. Accordingly, as with the radio analogy, in principle, asking whether a simpler version would work as well, depends on first figuring it out how the actual system works. As I have said, abstract models are less likely to be helpful there, because they don’t directly address the components.<br />
<br />
</div>Wouldn’t the airplane/bird analogy work here? Does being able to design an airplane help understanding how birds fly? I think it does. Evolution didn’t invent the wheel, so it had to go in a complex (and not necessarily very efficient) way to “design” locomotion, which means that airplane engines don’t really explain how birds propel themselves. On the other hand, both have wings, and controlling the flying devices looks pretty similar in the two cases. In the same way, if some artificial network can reproduce intelligent traits, we might be able to guide what we’re looking for in the brain (a model, whose necessity we agree on). Of course, scientific process rarely works in this way, but it’s because you need computers for this kind of “experimentation”, and computers are quite new.<br />
<br />
Balázs<br />
<br />
<br />
—<br />
Balazs Kegl<br />
Research Scientist (DR2)<br />
Linear Accelerator Laboratory<br />
CNRS / University of Paris Sud<br />
<a href="http://users.web.lal.in2p3.fr/kegl" target="1">http://users.web.lal.in2p3.fr/kegl</a><br />
<br />
<br />
<br />
<br />
<br />
</blockquote></div><br /></div>
</div></blockquote></div>