CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding

TL;DR

CogDPM introduces a novel diffusion probabilistic model inspired by cognitive predictive coding, incorporating precision weighting to enhance real-world forecasting accuracy in climate data prediction tasks.

Contribution

This work connects diffusion probabilistic models with cognitive predictive coding, integrating a precision weighting mechanism for improved real-world prediction performance.

Findings

CogDPM outperforms existing models in climate data forecasting.

Precision weights effectively estimate data predictability.

Demonstrates the connection between diffusion models and cognitive theories.

Abstract

Predictive Coding (PC) is a theoretical framework in cognitive science suggesting that the human brain processes cognition through spatiotemporal prediction of the visual world. Existing studies have developed spatiotemporal prediction neural networks based on the PC theory, emulating its two core mechanisms: Correcting predictions from residuals and hierarchical learning. However, these models do not show the enhancement of prediction skills on real-world forecasting tasks and ignore the Precision Weighting mechanism of PC theory. The precision weighting mechanism posits that the brain allocates more attention to signals with lower precision, contributing to the cognitive ability of human brains. This work introduces the Cognitive Diffusion Probabilistic Models (CogDPM), which demonstrate the connection between diffusion probabilistic models and PC theory. CogDPM features a precision estimation method based on the hierarchical sampling capabilities of diffusion models and weight the guidance with precision weights estimated by the inherent property of diffusion models. We experimentally show that the precision weights effectively estimate the data predictability. We apply CogDPM to real-world prediction tasks using the United Kindom precipitation and ERA surface wind datasets. Our results demonstrate that CogDPM outperforms both existing domain-specific operational models and general deep prediction models by providing more proficient forecasting.