CACTUS: a Comprehensive Abstraction and Classification Tool for Uncovering Structures
This addresses the problem of interpretability and efficiency in AI for domains like healthcare, but appears incremental as it builds on existing explainable AI methods.
The paper tackles the challenge of developing AI solutions with small datasets and opaque deep learning models by presenting CACTUS, a tool for improved secure analytics using explainable AI, which was assessed on breast cancer and thyroid datasets.
The availability of large data sets is providing an impetus for driving current artificial intelligent developments. There are, however, challenges for developing solutions with small data sets due to practical and cost-effective deployment and the opacity of deep learning models. The Comprehensive Abstraction and Classification Tool for Uncovering Structures called CACTUS is presented for improved secure analytics by effectively employing explainable artificial intelligence. It provides additional support for categorical attributes, preserving their original meaning, optimising memory usage, and speeding up the computation through parallelisation. It shows to the user the frequency of the attributes in each class and ranks them by their discriminative power. Its performance is assessed by application to the Wisconsin diagnostic breast cancer and Thyroid0387 data sets.