<div dir="ltr">Hey Larry! Good to hear from you again :)<div><br></div><div>Could you post your question on the Nengo forum at <a href="https://forum.nengo.ai/">https://forum.nengo.ai/</a> ? We're in the process of phasing out this mailing list so that this kind of info is easy to google.</div><div><br></div><div>- Trevor</div></div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Jul 29, 2017 at 9:55 AM, Laurence Michaels <span dir="ltr"><<a href="mailto:lmichaels@mail.usf.edu" target="_blank">lmichaels@mail.usf.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div class="m_7063897152274798842gmail-abs m_7063897152274798842gmail-unselectable" id="m_7063897152274798842gmail-io-ox-core"><div class="m_7063897152274798842gmail-abs" id="m_7063897152274798842gmail-io-ox-screens"><div class="m_7063897152274798842gmail-abs" id="m_7063897152274798842gmail-io-ox-windowmanager"><div class="m_7063897152274798842gmail-atb" id="m_7063897152274798842gmail-io-ox-windowmanager-pane"><div class="m_7063897152274798842gmail-window-container m_7063897152274798842gmail-io-ox-mail-window m_7063897152274798842gmail-chromeless-window" id="m_7063897152274798842gmail-window-0"><div class="m_7063897152274798842gmail-window-container-center" style="width:100%"><div class="m_7063897152274798842gmail-window-body m_7063897152274798842gmail-classic-toolbar-visible m_7063897152274798842gmail-right-section-enabled"><div class="m_7063897152274798842gmail-abs m_7063897152274798842gmail-window-content m_7063897152274798842gmail-vsplit m_7063897152274798842gmail-preview-none"><div class="m_7063897152274798842gmail-rightside m_7063897152274798842gmail-mail-detail-pane m_7063897152274798842gmail-selection-one m_7063897152274798842gmail-preview-visible"><div class="m_7063897152274798842gmail-thread-view-control m_7063897152274798842gmail-abs m_7063897152274798842gmail-back-navigation-visible"><div class="m_7063897152274798842gmail-thread-view-list m_7063897152274798842gmail-scrollable m_7063897152274798842gmail-abs"><div class="m_7063897152274798842gmail-thread-view m_7063897152274798842gmail-list-view"><article class="m_7063897152274798842gmail-list-item m_7063897152274798842gmail-mail-item m_7063897152274798842gmail-mail-detail m_7063897152274798842gmail-f6-target m_7063897152274798842gmail-focusable m_7063897152274798842expanded" style="outline:0px"><section class="m_7063897152274798842gmail-body m_7063897152274798842gmail-user-select-text m_7063897152274798842gmail-focusable"><div class="m_7063897152274798842gmail-mail-detail-content m_7063897152274798842gmail-noI18n m_7063897152274798842gmail-colorQuoted m_7063897152274798842gmail-simple-mail" style="min-height:100px"><div id="m_7063897152274798842gmail-ox-ac41ec29b4"><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">Hi All,</span></p><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">This is Larry. I did the coin-flipping task at this summer's brain camp (which I loved). I'm still working on my project and have confirmed that my model consistently underestimates Alternations at a Probability of Alternation around 0.6. (This is the same area where people have a bias and will underestimate it as well.)</span></p><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">Now, I want to figure out why. My current theory is that the learning process is not stable/does not converge under this substantial uncertainty. To research this, I've created a probe to look at the neural weights. I have a two dimensional input ensemble (200 neurons) connected via PES learning to a one dimensional prediction (100 neurons). When I use a probe on the connection to get the weights, it is 3 dimensions:<br></span></p><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">- dimension 0 is the time during the learning. The range for this index varies depending upon the 'sample_every' parameter.<br></span></p><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">- dimension 1 only has a range of 1 (value = 0)<br></span></p><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">- dimension 2 has a range of 200 (the size of my input ensemble)</span></p><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">I expected the weights to have 3 dimensions (time, 200 for the input ensemble, 100 for the output ensemble). I seem to be mis-understanding something. What are the definitions of the dimensions? Any thoughts or advice? </span></p><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">Best,<br></span></p><p><span style="color:rgb(51,51,51);font-family:helvetica,arial,sans-serif;font-size:12pt">Larry</span></p></div></div></section></article></div></div></div></div></div></div></div></div></div></div></div></div><div id="m_7063897152274798842gmail-tmp" style="display:none"></div>
&amp;lt;p class="noscript"&amp;gt;<wbr>This app uses JavaScript. Your browser either doesn't support JavaScript or you have it turned off. To use this app please use a JavaScript enabled browser.&amp;lt;/p&<wbr>amp;gt;</div>
<br>______________________________<wbr>_________________<br>
nengo-user mailing list<br>
<a href="mailto:nengo-user@artsservices.uwaterloo.ca">nengo-user@artsservices.<wbr>uwaterloo.ca</a><br>
<a href="https://artsservices.uwaterloo.ca/mailman/listinfo/nengo-user" rel="noreferrer" target="_blank">https://artsservices.<wbr>uwaterloo.ca/mailman/listinfo/<wbr>nengo-user</a><br>
<br></blockquote></div><br></div>