Adrian Hill is a PhD student in the Machine Learning Group at TU Berlin.
Dithering algorithms are a group of color quantization techniques that create the illusion of continuous color in images with small color palettes by adding high-frequency noise or patterns. Traditionally used in printing, they are now mostly used for stylistic purposes.
DitherPunk.jl implements a wide variety of fast and extensible dithering algorithms. Using its example, I will demonstrate how packages for creative coding can be built on top of the JuliaImages ecosystem.
In pursuit of interpreting black-box models such as deep image classifiers, a number of techniques have been developed that attribute and visualize the importance of input features with respect to the output of a model.
ExplainableAI.jl brings several of these methods to Julia, building on top of primitives from the Flux ecosystem. In this talk, we will give an overview of current features and show how the package can easily be extended, allowing users to implement their own methods and rules.