Predictive Coding beyond Correlations
This work addresses the challenge of integrating causal inference into neural models for researchers in machine learning and neuroscience, though it appears incremental as it builds on existing predictive coding methods.
The paper tackles the problem of enabling predictive coding, a biologically plausible algorithm, to perform causal inference tasks by modifying its inference process to compute interventions without altering causal graphs, and shows empirical improvements in image classification performance.
Recently, there has been extensive research on the capabilities of biologically plausible algorithms. In this work, we show how one of such algorithms, called predictive coding, is able to perform causal inference tasks. First, we show how a simple change in the inference process of predictive coding enables to compute interventions without the need to mutilate or redefine a causal graph. Then, we explore applications in cases where the graph is unknown, and has to be inferred from observational data. Empirically, we show how such findings can be used to improve the performance of predictive coding in image classification tasks, and conclude that such models are able to perform simple end-to-end causal inference tasks.