Beyond Turing: Memory-Amortized Inference as a Foundation for Cognitive Computation

TL;DR

This paper introduces Memory-Amortized Inference (MAI), a novel framework modeling cognition as inference over memory cycles, emphasizing structured reuse and topological memory to explain intelligence and its relation to reinforcement learning.

Contribution

The paper proposes MAI as a new formal framework for cognitive computation, linking it to cortical algorithms and duality with reinforcement learning, with implications for AGI.

Findings

MAI models cortical columns as local inference over memory cycles.

MAI provides a dual perspective to reinforcement learning, reconstructing causes from memory.

MAI offers a biologically grounded foundation for energy-efficient AI inference.

Abstract

Intelligence is fundamentally non-ergodic: it emerges not from uniform sampling or optimization from scratch, but from the structured reuse of prior inference trajectories. We introduce Memory-Amortized Inference (MAI) as a formal framework in which cognition is modeled as inference over latent cycles in memory, rather than recomputation through gradient descent. MAI systems encode inductive biases via structural reuse, minimizing entropy and enabling context-aware, structure-preserving inference. This approach reframes cognitive systems not as ergodic samplers, but as navigators over constrained latent manifolds, guided by persistent topological memory. Through the lens of delta-homology, we show that MAI provides a principled foundation for Mountcastle's Universal Cortical Algorithm, modeling each cortical column as a local inference operator over cycle-consistent memory states. Furthermore, we establish a time-reversal duality between MAI and reinforcement learning: whereas RL propagates value forward from reward, MAI reconstructs latent causes backward from memory. This inversion paves a path toward energy-efficient inference and addresses the computational bottlenecks facing modern AI. MAI thus offers a unified, biologically grounded theory of intelligence based on structure, reuse, and memory. We also briefly discuss the profound implications of MAI for achieving artificial general intelligence (AGI).