Date: Fri, 22 Sep 2017 15:00:00 +0000
<p class="p1"><span class="s1">One Shot Learning is the class of machine learning procedures that focuses learning something from a small number of examples.<span class="Apple-converted-space"> </span> This is in contrast to "traditional" machine learning which typically requires a very large training set to build a reasonable model.</span></p> <p class="p1"><span class="s1">In this episode, Kyle presents a coded message to Linhda who is able to recognize that many of these new symbols created are likely to be the same symbol, despite having extremely few examples of each.<span class="Apple-converted-space"> </span> Why can the human brain recognize a new symbol with relative ease while most machine learning algorithms require large training data?<span class="Apple-converted-space"> </span> We discuss some of the reasons why and approaches to One Shot Learning.</span></p>
