Hacker's guide to Neural Networks

Some more good posts when it was submitted last year: <a href="https://news.ycombinator.com/item?id=8553307" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=8553307</a>

Visualizing training of CNN in browser allows to anybody quickly get the ideas behind. A while ago, I was looking for things like &quot;xyz applet&quot; to get intuition about xyz. This is exactly what is going on here. Great respect to the author!

Nice introduction to backpropagation. The author understandably handles only a special case and avoids the case when an input comes in on many completely different paths to the output. When this article will be extended, it would be interesting to read about the case when it is not that way. (e.g. convnets with parameter sharing).

For those playing along at home (like me): even though it&#x27;s only to highlight the idea, there&#x27;s a bug in the &quot;Random Local Search&quot; loop. It should be `x_try = best_x + tweak_amount...` best_x, not x. Same for y. I was wondering why it wasn&#x27;t improving even with 1e10 iterations ;)

Finally, there is a neural networked way of learning neural network! Thanks..

Also see non-NN topics in the field of AGI. NN is just the most popular mainstream approach lineage.

With all respect to this PhD candidate, if you&#x27;re serious about this, you&#x27;re not doing it in Javascript.<p>And if you&#x27;re serious about learning it, you&#x27;d plop down the $149 for the Home edition of Matlab plus the $45 for the neural net toolbox. Or take a statistics class and grab the $99 student edition, which comes with the machine learning toolbox.<p>If you&#x27;re gonna learn some shit, learn some shit. Calling Math.* to calculate rise over run in Javascript isn&#x27;t where it&#x27;s at.<p>Or maybe I&#x27;m just grumpy because I interviewed a Caltech CS grad last week who flat out did not know C. Never touched it in his studies. World&#x27;s gone nuts.