<div dir="ltr">Although the analogies are somewhat stretched, there is this:<div><br></div><div><a href="http://colah.github.io/posts/2015-09-NN-Types-FP/">http://colah.github.io/posts/2015-09-NN-Types-FP/</a><br></div><div><br></div><div>Tom</div></div><div class="gmail_extra"><br><div class="gmail_quote">On Wed, Jan 3, 2018 at 11:03 AM, Johannes Waldmann <span dir="ltr"><<a href="mailto:johannes.waldmann@htwk-leipzig.de" target="_blank">johannes.waldmann@htwk-leipzig.de</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Dear Cafe,<br>
<br>
I like this paper (R. Lämmel in SCP 2008) very much<br>
<a href="https://userpages.uni-koblenz.de/~laemmel/MapReduce/" rel="noreferrer" target="_blank">https://userpages.uni-koblenz.<wbr>de/~laemmel/MapReduce/</a><br>
both for contents and for style -<br>
<br>
and I wonder if there's something similar ("Haskell for design<br>
recovery", "rigorous description", "executable specification")<br>
on deep learning.<br>
<br>
Mainly for understanding/teaching without all the hype.<br>
(But of course, an accelerate-* implementation would be nice.)<br>
<br>
Yes I know that hyperbole *is* the main thing in this area.<br>
<br>
Happy New Year - J.<br>
______________________________<wbr>_________________<br>
Haskell-Cafe mailing list<br>
To (un)subscribe, modify options or view archives go to:<br>
<a href="http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe" rel="noreferrer" target="_blank">http://mail.haskell.org/cgi-<wbr>bin/mailman/listinfo/haskell-<wbr>cafe</a><br>
Only members subscribed via the mailman list are allowed to post.</blockquote></div><br></div>