From data to concepts via wiring diagrams
This work addresses the challenge of concept extraction from data for applications in autonomous systems, but it appears incremental as it combines existing techniques from multiple fields.
The paper tackled the problem of extracting abstract concepts (wiring diagrams) from sequential data by introducing quasi-skeleton wiring diagram graphs and proving their correspondence to Hasse diagrams, resulting in algorithms that correctly identified winning strategies for an autonomous agent in a computer game.
A wiring diagram is a labeled directed graph that represents an abstract concept such as a temporal process. In this article, we introduce the notion of a quasi-skeleton wiring diagram graph, and prove that quasi-skeleton wiring diagram graphs correspond to Hasse diagrams. Using this result, we designed algorithms that extract wiring diagrams from sequential data. We used our algorithms in analyzing the behavior of an autonomous agent playing a computer game, and the algorithms correctly identified the winning strategies. We compared the performance of our main algorithm with two other algorithms based on standard clustering techniques (DBSCAN and agglomerative hierarchical), including when some of the data was perturbed. Overall, this article brings together techniques in category theory, graph theory, clustering, reinforcement learning, and data engineering.