Glad to help Jesse! There is no clear line between ANNs and BNNs,<br>and lots of Computational Neuroscientists and Computer Scientists<br>are keen on combining them.<br><br>The major benefit of ANNs is that there are backpropagation algorithms<br>
guaranteed to effectively train them, whereas no such algorithms are<br>out there for BNNs. For training BNNs, some people look to biological<br>training routines that work like spike-timing-dependent-plasticity:<br><br><a href="http://en.wikipedia.org/wiki/Spike-timing-dependent_plasticity">http://en.wikipedia.org/wiki/Spike-timing-dependent_plasticity</a><br>
<br>Recently some people came up with a "tempotron", a biologically-<br>plausible neuron that can be trained to recognize temporal sequences:<br><br><a href="http://www.nature.com/neuro/journal/v9/n3/abs/nn1643.html">http://www.nature.com/neuro/journal/v9/n3/abs/nn1643.html</a><br>
<br>I'm sure over time the two fields will converge even further, looking<br>forward to talking more about it soon. Thanks for the questions!<br><br> mike<br><br><br><br><div class="gmail_quote">On Mon, Jan 3, 2011 at 2:16 PM, Jesse welz <span dir="ltr"><<a href="mailto:welzart@gmail.com">welzart@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">Mike,<br>
<br>
Thank you for the clarification. That totally makes sense and I kind<br>
of remember coming across some info explaining the differences of BNNs<br>
and ANNs. I'll bet the two types of networks could be combined<br>
although there is probably no use for such a combination.<br>
<br>
I will definitely try and make that workshop as I find A.I. absolutely<br>
fascinating. I've always wanted to sit in on one of the Machine<br>
Learning workshops but never had the chance. This gives me good excuse<br>
to make sure I show up.<br>
<br>
Gescykae<br>
<div><div></div><div class="h5"><br>
On Mon, Jan 3, 2011 at 2:04 PM, Mike Schachter <<a href="mailto:mike@mindmech.com">mike@mindmech.com</a>> wrote:<br>
> Hi Jesse,<br>
><br>
> I don't have much familiarity with B.E.A.M robotics, but I did<br>
> read through this FAQ:<br>
><br>
> <a href="http://faq.solarbotics.net/FAQ.html#q3" target="_blank">http://faq.solarbotics.net/FAQ.html#q3</a><br>
><br>
> The workshop is focusing on artificial neural networks, which<br>
> are not the same as biological neural networks. If B.E.A.M<br>
> robots are based on analog RC circuits, then they're more<br>
> biological NNs (BNNs) than artificial NNs (ANNs).<br>
><br>
> There are many similarities between biological and artificial<br>
> neural networks that I'd be happy to talk about though. For<br>
> example the layered network structure is similar between the<br>
> two. The theory behind ANNs are more developed than for<br>
> BNNs, but the two fields play off eachother heavily.<br>
><br>
> The difference between the two types of networks is in how<br>
> complex the model for an individual neuron is. A neuron in<br>
> an ANN is typically less complex than a neuron in a BNN,<br>
> which makes it easier to analyze mathematically and also<br>
> to simulate and train on a computer.<br>
><br>
> I'd be happy to elaborate via the list or in person, the machine<br>
> learning group meets up every Wednesday at 7:30pm in the<br>
> back classroom.<br>
><br>
> mike<br>
><br>
> On Mon, Jan 3, 2011 at 1:56 PM, Jesse welz <<a href="mailto:welzart@gmail.com">welzart@gmail.com</a>> wrote:<br>
>><br>
>> Hi Mike,<br>
>><br>
>> Are the neural networks you're talking about here at all related to<br>
>> the neural networks that B.E.A.M. robotics are based on? I know<br>
>> nothing about neural networks other than what I've picked up tinkering<br>
>> with B.E.A.M. robotics. Even if they are not related I would love<br>
>> learn more and become Neural Network Aware. I am not a mathematician<br>
>> nor a programmer but have dabbled in both. Will I be able to follow<br>
>> along?<br>
>><br>
>> Best,<br>
>> Gescykae<br>
>> _______________________________________________<br>
>> Noisebridge-discuss mailing list<br>
>> <a href="mailto:Noisebridge-discuss@lists.noisebridge.net">Noisebridge-discuss@lists.noisebridge.net</a><br>
>> <a href="https://www.noisebridge.net/mailman/listinfo/noisebridge-discuss" target="_blank">https://www.noisebridge.net/mailman/listinfo/noisebridge-discuss</a><br>
><br>
><br>
_______________________________________________<br>
Noisebridge-discuss mailing list<br>
<a href="mailto:Noisebridge-discuss@lists.noisebridge.net">Noisebridge-discuss@lists.noisebridge.net</a><br>
<a href="https://www.noisebridge.net/mailman/listinfo/noisebridge-discuss" target="_blank">https://www.noisebridge.net/mailman/listinfo/noisebridge-discuss</a><br>
</div></div></blockquote></div><br>