aria42 — Musings on everything and then some

tl;dr: I wrote Flare, a Dynamic Neural Net library in Clojure. It currently can do some non-trivial things and it’s pretty fast: over 3x faster than PyTorch for a CPU-based a simple Bi-LSTM classifier (although PyTorch has many more features and is more...

I can’t be objective about the Smashing Pumpkins. I was so deep in the throes of adolescence when Mellon Collie and the Infinite Sandess was released that the intended irony of the album’s name was lost upon me. Billy Corgan’s voice will always make...

$$\newcommand{\hessian}{\mathbf{H}}\newcommand{\grad}{\mathbf{g}}\newcommand{\invhessian}{\mathbf{H}^{-1}}\newcommand{\qquad}{\hspace{1em}}$$
Numerical optimization is at the core of much of machine learning. Once you’ve defined your model and have a dataset ready, estimating the parameters of your model typically boils down to minimizing some multivariate function $f(x)$, where the input...

A few people from my last post asked for an accessible explanation of the margin infused relaxation algorithm (MIRA) and confidence-weighted learning (CW) classification algorithms I discussed. I don’t think I can easily explain CW, but I think MIRA...