<html><head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
</head><body style="font-family: tt;" bgcolor="#FFFFFF" text="#000000"><div
style="font-family: tt;"><span style="font-family: monospace;">Hi
Brian,<br><br>Nengo uses the NEF (neural engineering framework) to
compute the weights. You can think of this as an efficient learning
algorithm if you want, so the 'patterns' are the sample points in the
functions you've defined that you want computed. A python description
of the NEF algorithm can be found here:<br><br><a class="moz-txt-link-freetext" href="http://nengo.ca/docs/html/nef_algorithm.html">http://nengo.ca/docs/html/nef_algorithm.html</a><br><br>Best,<br>Chris<br></span><br>Brian
Krainer wrote:<blockquote
cite="mid:CAMQ3wvOLnpE6F8Z+ut1pt_CTNGJ5UtQS7YzEzxeKy91k-BZn5g@mail.gmail.com"
type="cite"><meta http-equiv="Content-Type" content="text/html;
charset=UTF-8"><div dir="ltr">I'm a little confused on how weights
between neurons are calculated. In previous neural network software I've
used, the network had to be trained on specific patterns in order to
calculate the correct weights (using algorithms like back propagation.)
It seems that with nengo the weights are computed without seeing any
patterns. How is this being done?<div>
<br></div><div>Thanks,</div><div><br></div><div>Brian</div></div>
<pre wrap="">_______________________________________________
nengo-user mailing list
<a class="moz-txt-link-abbreviated" href="mailto:nengo-user@ctnsrv.uwaterloo.ca">nengo-user@ctnsrv.uwaterloo.ca</a>
<a class="moz-txt-link-freetext" href="http://ctnsrv.uwaterloo.ca/mailman/listinfo/nengo-user">http://ctnsrv.uwaterloo.ca/mailman/listinfo/nengo-user</a>
</pre></blockquote></div></body></html>