http://asymptoticlabs.com/enContents © 2022 <a href="mailto:quidditymaster@gmail.com">Tim Anderton</a> Wed, 31 Aug 2022 21:28:18 GMTNikola (getnikola.com)http://blogs.law.harvard.edu/tech/rsshttp://asymptoticlabs.com/posts/skm-embedding-of-mnist.htmlTim Anderton<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt"> </div><div class="inner_cell"> <div class="text_cell_render border-box-sizing rendered_html"> <p>I recently thought up a machine learning algorithm called <a href="http://asymptoticlabs.com/asymptoticlabs.com/blog/posts/smooth-kernel-machines.html">"Smooth Kernel Macines" (SKM)</a>. In this post I will try out SKM on the ever ubiquitous MNIST dataset. The goal of this post is not so much to achieve state of the art performance on MNIST (though that would be nice), as it is to simply try out SKM on a familiar and well understood dataset.</p> <p>tldr; I achieve a respectable 0.006 error rate using an SKM type layer on top of a convolutional neural net feature extractor. An SKM output layer works a little better than a K way softmax (at least for MNIST). SKM trains faster, and comes with an accurate built in measure of prediction confidence.</p> <p><a href="http://asymptoticlabs.com/posts/skm-embedding-of-mnist.html">Read more…</a> (26 min remaining to read)</p></div></div></div></body></html> embeddingsmachine learningMNISTSKMhttp://asymptoticlabs.com/posts/skm-embedding-of-mnist.htmlFri, 06 Apr 2018 06:00:00 GMT