ELDON.IO

I build tools to help people understand, debug, and interpret ML models by combining traditional software engineering and explainable AI techniques. My work employs design and systems-building methodologies at the intersection of HCI and ML research. My previous projects have fused sensing, ML, and novel AR interfaces to guide users through physical tasks... I am advised by Björn Hartmann and affiliated with the Berkeley Institute of Design... Umlaut supports users in debugging neural networks by running heuristic checks on the ML program's structure and model behavior during runtime. Umlaut's checking infrastructure can be added to a Keras runtime with minimal changes to the source program (2 lines of code). Raised errors are presented in an interface which tightly couples tutorial-based explanations, visualizations of model output, context from program runtime, and links back to source code.