2 papers
cs.AI2026
Transformers are Bayesian Networks
Gregory Coppola
Transformers are the dominant architecture in AI, yet why they work remains poorly understood. This paper offers a precise answer: a transformer is a Bayesian network. We establish…
cs.AI2026
Statistical Parsing for Logical Information Retrieval
Greg Coppola
In previous work (Coppola, 2024) we introduced the Quantified Boolean Bayesian Network (QBBN), a logical graphical model that implements the forward fragment of natural deduction (…