cPerceptron: A neural network (Simple Perceptron) implemented in PHP.

This makes me think I should upload my random computational intelligence assignments and get sweet, delicious karma.<p>Edit: OK, I was a bit snarky, but I'm serious.<p>I see these things on HN all the time. These are, quite literally, undergraduate projects.<p>I don't see people upvoting "My First Stack" or "Check out this Pet Shop I wrote in J2EE". Computational intelligence is not some land of super wise geniuses that mere mortals cannot ascend to. It's all pretty straightforward.<p>Eg, my Ant Colony Optimiser for a Travelling Salesman Problem:<p><a href="https://github.com/jchester/ruby-ry48p-aco" rel="nofollow">https://github.com/jchester/ruby-ry48p-aco</a><p>and my Genetic Algorithm for optimising Ackley's Function:<p><a href="https://github.com/jchester/ruby-ackley-genetic-algorithm" rel="nofollow">https://github.com/jchester/ruby-ackley-genetic-algorithm</a>

Nice. Sort of the computational equivalent of 'A model of Neuschwannstein Castle made out of spaghetti'.

That's pretty neatly written code!<p>If you've mastered PHP then you could easily make the switch to C or C++ for a very large speedboost while still being able to recycle a large chunk of your code. PHP and C look quite alike (drop the $ signs and add declarations and you're halfway there).<p>Neat to see you interested in doing more advanced stuff than just web bits and pieces.

Always nice to see these pet projects as proof of concept for ML in PHP. There's a bunch of them, but the more, the merrier.

I find it quite interesting how PHP developers try their best to encrypt their function names as much as possible? rdmFloat? Why not randomFloat or random_float?<p>This particular example isn't very problematic, but I see this pattern in PHP way more than in other languages.

Ha! You've triggered me to put my own PHP multi-layered neural network on GitHub. Available for forks &#38; downloads here: <a href="https://github.com/infostreams/neural-network" rel="nofollow">https://github.com/infostreams/neural-network</a>

ok whats the point? what can i train with this? what kind of outputs can i get?