Giacomo Indiveri :emacs:🧠<p>I am really proud to announce that our latest effort on showing the advantages of our analog/digital <a href="https://fediscience.org/tags/neuromorphic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuromorphic</span></a> spiking neural network chips in solving complex biomedical applications has just been published here: <a href="https://rdcu.be/ef5N0" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">rdcu.be/ef5N0</span><span class="invisible"></span></a> </p><p>The demonstrates that *small* *highly variable* and *low accuracy* <a href="https://fediscience.org/tags/SNNs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SNNs</span></a> can indeed be useful, without having to resort to <a href="https://fediscience.org/tags/backprop" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>backprop</span></a> in large-scale <a href="https://fediscience.org/tags/DNNs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DNNs</span></a>! 😉</p>