LMU Dissertation Recasts Neural Networks as Cybernetic Error-Controlled Regulators on the Path to AGI
sebkrier · x · 2026-11-15
A forwarded LMU Munich dissertation, "Knowledge transfer in cognitive systems theory: models, computation, and explanation," argues that knowledge transfer can be explicated via structure mapping and control: an effective model's structure enables adaptive control in new domains.
Key points:
- Advocates a model-based view of computation; artificial neural networks are model-based and best understood as error-controlled regulators in the cybernetic tradition.
- Automated transfer learning from pre-trained networks counts as progress toward AGI, since it automates a general systems methodology of knowledge transfer akin to scientific reasoning.
- Discusses analogical reasoning (viewed by some as the core of cognition), a physics case study, an extended Bayesian account of confirmation via structural mapping, and quantum-like models in cognition.
More from AGI Musings
- SfN2026 minisymposium on embodied computation spans zebrafish whole-brain dynamics to NeuroAgents — tweetsatpreet · 2026-11-15
- Patient data that never leaves the hospital is the easiest AI project to get approved — MaziyarPanahi · 2026-11-15
- Blogger argues anti-AI sentiment is a psyop by old creative-industry gatekeepers — nptacek · 2026-11-15
- What happens when AI trains on AI content for 100 generations? — Huge-Conference-1193 · 2026-11-15
- The Strangest AGI Outcome: Humans Stop Being the Audience for New Knowledge — VraserX · 2026-11-15
- Berkeley Legend Patterson Predicts Superintelligent Chef Robots Within Two Years — davidpattersonx · 2026-11-15