<div dir="ltr">This is actually pretty interesting to think about.<div><br>1) Are Tensorflow and related libraries actually probabilistic like I'm assuming? My uneducated abstraction is that they iterate over the data set using some sort of randomization to create "rules" then apply them. </div><div>2) If so, how do you test them? Do you do multiple iterations of a test and look at the distribution? </div><div>3) How do you avoid "local minima", so to speak. I saw a "step size" reference in the article, is this how much the attempted algorithms change each time?</div><div><br></div><div>Thanks!</div><div>JS</div></div><div class="gmail_extra"><br><div class="gmail_quote">On Wed, May 25, 2016 at 11:13 PM, JS Irick <span dir="ltr"><<a href="mailto:hundredpercentjuice@gmail.com" target="_blank">hundredpercentjuice@gmail.com</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">I can't tell if you're trolling or not.<div><br></div><div>He should have written unit tests for his machine learning program? On the plus side, that's one the best definition of "results oriented" I've heard.</div></div><div class="gmail_extra"><div><div class="h5"><br><div class="gmail_quote">On Wed, May 25, 2016 at 10:46 PM, Michael Tamillow <span dir="ltr"><<a href="mailto:mikaeltamillow96@gmail.com" target="_blank">mikaeltamillow96@gmail.com</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">He should have wrote some unit tests first!</div><div class="gmail_extra"><br><div class="gmail_quote"><span>On Wed, May 25, 2016 at 5:29 PM, Joshua Herman <span dir="ltr"><<a href="mailto:zitterbewegung@gmail.com" target="_blank">zitterbewegung@gmail.com</a>></span> wrote:<br></span><div><div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">I saw that on Hn . The funniest thing is that at the end the trained tensor flow network doesn't even return the correct values after it is trained. <br><div><div><div class="gmail_quote"><div dir="ltr">On Wed, May 25, 2016 at 5:09 PM Robare, Phillip (TEKSystems) <<a href="mailto:proba@allstate.com" target="_blank">proba@allstate.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Joel Grus (author of O'Reilly's "Data Science from Scratch: First Principles with Python") has written a hilarious post about being asked to write FizzBuzz in a Python interview. So he sets up a neural network. Check out <a href="http://joelgrus.com/2016/05/23/fizz-buzz-in-tensorflow/" rel="noreferrer" target="_blank">http://joelgrus.com/2016/05/23/fizz-buzz-in-tensorflow/</a><br>
<br>
Of course, as one of the comments points out, if you have to do fizzbuzz in Java there is the Enterprise version of FizzBuzz with all the GoF patterns: <a href="https://github.com/EnterpriseQualityCoding/FizzBuzzEnterpriseEdition" rel="noreferrer" target="_blank">https://github.com/EnterpriseQualityCoding/FizzBuzzEnterpriseEdition</a>.<br>
<br>
<br>
Phil Robare<br>
_______________________________________________<br>
Chicago mailing list<br>
<a href="mailto:Chicago@python.org" target="_blank">Chicago@python.org</a><br>
<a href="https://mail.python.org/mailman/listinfo/chicago" rel="noreferrer" target="_blank">https://mail.python.org/mailman/listinfo/chicago</a><br>
</blockquote></div>
</div></div><br>_______________________________________________<br>
Chicago mailing list<br>
<a href="mailto:Chicago@python.org" target="_blank">Chicago@python.org</a><br>
<a href="https://mail.python.org/mailman/listinfo/chicago" rel="noreferrer" target="_blank">https://mail.python.org/mailman/listinfo/chicago</a><br>
<br></blockquote></div></div></div><br></div>
<br>_______________________________________________<br>
Chicago mailing list<br>
<a href="mailto:Chicago@python.org" target="_blank">Chicago@python.org</a><br>
<a href="https://mail.python.org/mailman/listinfo/chicago" rel="noreferrer" target="_blank">https://mail.python.org/mailman/listinfo/chicago</a><br>
<br></blockquote></div><br><br clear="all"><div><br></div></div></div><span class="">-- <br><div>====<br>JS Irick<br><a href="tel:312-307-8904" value="+13123078904" target="_blank">312-307-8904</a><br>Consultant: <a href="http://truqua.com" target="_blank">truqua.com</a><br>Coach: <a href="http://atlascrossfit.com" target="_blank">atlascrossfit.com</a><br>Programmer: <a href="http://juicetux.com" target="_blank">juicetux.com</a></div>
</span></div>
</blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature">====<br>JS Irick<br>312-307-8904<br>Consultant: <a href="http://truqua.com" target="_blank">truqua.com</a><br>Coach: <a href="http://atlascrossfit.com" target="_blank">atlascrossfit.com</a><br>Programmer: <a href="http://juicetux.com" target="_blank">juicetux.com</a></div>
</div>