Predicting responses helps reveal system states beyond direct observation
Ontic state recovery through prediction
Machine LearningArtificial Intelligence
Summary
When we interact with a system, we see only its responses, not its full internal state. The authors define a system’s state as how it responds to all possible questions in a given set. They examine how predicting future responses can give insight into the whole state, not just individual predictions. Using synthetic systems and neural data, they explore how precise prediction relates to understanding the entire system state.
What this means in practice
- •For machine learning engineers: Improve model interpretation by linking prediction accuracy to the completeness of learned system states.
- •For neuroscience data analysts: Use response prediction methods to better understand underlying neural states in brain recordings.
Tested on simulated data.
Authors
Ping Zhang, Quang-Huy Nguyen, Yingtie Lei, Wei-Lun Chao
Abstract
We encounter a system through its responses, yet its state concerns how the system is. Predicting further responses promises knowledge beyond what is immediately observed. What that knowledge tells us about the system's state depends on what we mean by a state in the first place. We give this notion a model-relative meaning: a state is the complete response profile over a specified query universe, and configurations agreeing on every query are regarded as the same state. From this perspective, a learned state is understood through the distinctions between these profiles that it retains. Prediction concerns selected observations; recovery concerns the profile as a whole. We examine their relationship through query ambiguity, state-space geometry, and the choice of prediction targets. Synthetic systems with known response laws and neural recordings provide complementary settings for this investigation. The aim is to clarify how prediction can become a way of knowing a system, and what it would mean for a learned state to preserve the state being studied.