XAI&I: Closing the Accuracy Gap Between Self-Explanatory AI and Black Box Convolutional Neural Networks

Theodor Kozlowski


Supervised by Catherine Teehan; Moderated by Steven Schockaert

Using the research conducted in the paper “XAI&I: Self-explanatory Ai facilitating mutual understanding between AI and human experts” (Grange et al. 2022), explore (through data analysis) and build upon the algorithms existing methodology to improve accuracy and feature intelligibility. This can be done through incorporating additional layers, additional networks, manipulation of the input data, or other exploratory means.

Final Report (25/10/2023) [Zip Archive]

Publication Form