Comprehensive optical design, optimization, and analysis in Python.

Simple skeleton for easy implementations of CA in python and numpy/torch, visualizing with pygame

Full integration of animated javascript-based visualizations (D3, vega-lite, semiotic, etc ...) into Reveal.js presentations

PyTorch-based code for training fully-connected and convolutional networks using backpropagation (BP), feedback alignment (FA), direct feedback alignment (DFA), and direct random target projection …

Interactively inspect module inputs, outputs, parameters, and gradients.

Latex code for making neural networks diagrams

This is pydoctor, an API documentation generator that works by static analysis.

Unified algorithmic framework for reconstructing signals with finite rate of innovation

Convert an inline LATEX equation into SVG path using Python for Inkscape