2021/03/30 by James Clift, Daniel Murfet, Clift, James +3
Computer Science · #Artificial Intelligence (cs.AI) #Computability, Logic, AI Algorithms #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Programming Languages (cs.PL) #Quantum Computing Algorithms and Architecture #cs.AI #cs.LG #cs.PL
paper · pdf · doi:10.48550/arxiv.2103.16080
16 pages, 7 figures
arxiv created 2021/03/30 · openalex publication_date 2021/03/30 · arxiv updated 2021/03/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We re-evaluate universal computation based on the synthesis of Turing machines. This leads to a view of programs as singularities of analytic varieties or, equivalently, as phases of the Bayesian posterior of a synthesis problem. This new point of view reveals unexplored directions of research in program synthesis, of which neural networks are a subset, for example in relation to phase transitions, complexity and generalisation. We also lay the empirical foundations for these new directions by reporting on our implementation in code of some simple experiments.