I hate to be a curmudgeon but is machine learning really necessary for a wavelet decompose?<p>Can anyone give an example where this enables you do to things that couldn't be done better with other techniques?
Note that chart appears to not work on iOS, as Plot.ly is erroneously snowing a "Webgl not supported" message (which is an error on their end, as the official website for the library shows the same issue. Issue on GitHub: <a href="https://github.com/plotly/plotly.js/issues/280" rel="nofollow">https://github.com/plotly/plotly.js/issues/280</a>)<p>That's a shame, as their API is pretty good, as this demo illustrates.
I haven't read much on gradient boosting, so questions:<p>1. Where is the gradient? This explanation makes it sound like a straight Generalized Additive Model.<p>2. In fact, the explanation makes it sounds worse than random forests. Wouldn't it quickly overfit? Where does the boosting come into play?