Towards a Solution to Bongard Problems: A Causal Approach [article]

Salahedine Youssef and Matej Zečević and Devendra Singh Dhami and Kristian Kersting
2022 arXiv   pre-print
To date, Bongard Problems (BP) remain one of the few fortresses of AI history yet to be raided by the powerful models of the current era. We present a systematic analysis using modern techniques from the intersection of causality and AI/ML in a humble effort of reviving research around BPs. Specifically, we first compile the BPs into a Markov decision process, then secondly pose causal assumptions on the data generating process arguing for their applicability to BPs, and finally apply
more » ... ent learning techniques for solving the BPs subject to the causal assumptions.
arXiv:2206.07196v1 fatcat:a3wjtp66tvg4noyuuip2y6bwei