<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>