This paper introduces Online Generalised Predictive Coding (ODEM), an extension of generalised filtering for real-time applications. ODEM enables simultaneous inference of latent states, learning of model parameters, and estimation of uncertainty. The method is demonstrated to effectively track latent states in complex, non-linear generative models, offering a biologically inspired approach to inference and learning in dynamic environments. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Introduces a biologically inspired framework for online inference and learning, potentially impacting how dynamic systems are modeled and understood.
RANK_REASON This is a research paper published on arXiv detailing a new methodology for online inference and learning.