How Causal Abstraction Underpins Computational Explanation

TL;DR

This paper explores how causal abstraction theory can explain how systems implement computations over representations, linking philosophical ideas with modern deep learning to improve understanding of generalization and prediction.

Contribution

It introduces a causal abstraction framework for understanding computational implementation in neural systems, connecting philosophy, cognition, and machine learning.

Findings

Causal abstraction provides a useful lens for analyzing neural computations.

The framework links representation, causality, and generalization in AI systems.

It offers insights into how neural networks implement computations over representations.

Abstract

Explanations of cognitive behavior often appeal to computations over representations. What does it take for a system to implement a given computation over suitable representational vehicles within that system? We argue that the language of causality -- and specifically the theory of causal abstraction -- provides a fruitful lens on this topic. Drawing on current discussions in deep learning with artificial neural networks, we illustrate how classical themes in the philosophy of computation and cognition resurface in contemporary machine learning. We offer an account of computational implementation grounded in causal abstraction, and examine the role for representation in the resulting picture. We argue that these issues are most profitably explored in connection with generalization and prediction.