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

• URL: http://arxiv.org/abs/2508.14143v1
• Date: Tue, 19 Aug 2025 15:10:26 GMT
• Title: Beyond Turing: Memory-Amortized Inference as a Foundation for Cognitive Computation
• Authors: Xin Li,
• Abstract summary: We introduce Memory-Amortized Inference (MAI) as a formal framework in which cognition is modeled as inference over latent cycles in memory.<n>We show that MAI provides a principled foundation for Mountcastle's Universal Cortical Algorithm.<n>We briefly discuss the profound implications of MAI for achieving artificial general intelligence.
• Score: 5.234742752529437
• License: http://creativecommons.org/publicdomain/zero/1.0/
• 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).

Related papers

• From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents [78.30630000529133]
  We propose MM-Mem, a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory.<n> MM-Mem memory structures hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic.<n>Experiments confirm the effectiveness of MM-Mem on both offline and streaming tasks.
  arXiv  Detail & Related papers  (2026-03-02T05:12:45Z)
• Understand Then Memory: A Cognitive Gist-Driven RAG Framework with Global Semantic Diffusion [14.538534837583931]
  Retrieval-Augmented Generation (RAG) effectively mitigates hallucinations in LLMs by incorporating external knowledge.<n>We propose CogitoRAG, a RAG framework that simulates human cognitive memory processes.<n>We show that CogitoRAG significantly outperforms state-of-the-art RAG methods, showcasing superior capabilities in complex knowledge integration and reasoning.
  arXiv  Detail & Related papers  (2026-02-11T12:58:08Z)
• Structured Episodic Event Memory [37.643537420763344]
  We propose Structured Episodic Event Memory (SEEM), a hierarchical framework that synergizes a graph memory layer for relational facts with a dynamic episodic memory layer for narrative progression.<n> Experimental results on the LoCoMo and LongMemEval benchmarks demonstrate that SEEM significantly outperforms baselines.
  arXiv  Detail & Related papers  (2026-01-10T03:17:25Z)
• PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency [50.712873697511206]
  Existing work often lacks adaptability to diverse tasks and overlooks the constructive and task-oriented role of AI agent memory.<n>We propose PISA, a pragmatic, psych-inspired unified memory system that treats memory as a constructive and adaptive process.<n>Our empirical evaluation, conducted on the existing LOCOMO benchmark and our newly proposed AggQA benchmark for data analysis tasks, confirms that PISA sets a new state-of-the-art by significantly enhancing adaptability and long-term knowledge retention.
  arXiv  Detail & Related papers  (2025-10-12T10:34:35Z)
• Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey [92.71325249013535]
  Deliberative tree search is a cornerstone of Large Language Model (LLM) research.<n>This paper introduces a unified framework that deconstructs search algorithms into three core components.
  arXiv  Detail & Related papers  (2025-10-11T03:29:18Z)
• A Unified Cortical Circuit Model with Divisive Normalization and Self-Excitation for Robust Representation and Memory Maintenance [2.705743343600661]
  We introduce a recurrent neural circuit that combines divisive normalization with self-excitation to achieve robust encoding.<n>We demonstrate the model's versatility in two canonical tasks.<n>This work establishes a unified mathematical framework that bridges noise suppression, working memory, and approximate Bayesian inference.
  arXiv  Detail & Related papers  (2025-08-18T08:00:24Z)
• Memory as Structured Trajectories: Persistent Homology and Contextual Sheaves [5.234742752529437]
  We introduce the delta-homology analogy, which formalizes memory as a set of sparse, topologically irreducible attractors.<n>A Dirac delta-like memory trace is identified with a nontrivial homology generator on a latent manifold of cognitive states.<n>We interpret these delta-homology generators as the low-entropy content variable, while the high-entropy context variable is represented dually as a filtration, cohomology class, or sheaf.
  arXiv  Detail & Related papers  (2025-08-01T23:03:13Z)
• Cycle-Consistent Helmholtz Machine: Goal-Seeded Simulation via Inverted Inference [5.234742752529437]
  We introduce the emphCycle-Consistent Helmholtz Machine (C$2$HM)<n>C$2$HM reframes inference as a emphgoal-seeded, emphasymmetric process grounded in structured internal priors.<n>By offering a biologically inspired alternative to classical amortized inference, $C2$HM reconceives generative modeling as intentional simulation.
  arXiv  Detail & Related papers  (2025-07-03T17:24:27Z)
• Latent Structured Hopfield Network for Semantic Association and Retrieval [52.634915010996835]
  Episodic memory enables humans to recall past experiences by associating semantic elements such as objects, locations, and time into coherent event representations.<n>We propose the Latent Structured Hopfield Network (LSHN), a framework that integrates continuous Hopfield attractor dynamics into an autoencoder architecture.<n>Unlike traditional Hopfield networks, our model is trained end-to-end with gradient descent, achieving scalable and robust memory retrieval.
  arXiv  Detail & Related papers  (2025-06-02T04:24:36Z)
• Temporal Model On Quantum Logic [0.0]
  The framework formalizes the evolution of propositions over time using linear and branching temporal models.<n>The hierarchical organization of memory is represented using directed acyclic graphs.
  arXiv  Detail & Related papers  (2025-02-09T17:16:53Z)
• Predictive Attractor Models [9.947717243638289]
  We propose textitPredictive Attractor Models (PAM), a novel sequence memory architecture with desirable generative properties. PAM avoids catastrophic forgetting by uniquely representing past context through lateral inhibition in cortical minicolumns. We show that PAM is trained with local computations through Hebbian plasticity rules in a biologically plausible framework.
  arXiv  Detail & Related papers  (2024-10-03T12:25:01Z)
• Topology-aware Embedding Memory for Continual Learning on Expanding Networks [63.35819388164267]
  We present a framework to tackle the memory explosion problem using memory replay techniques. PDGNNs with Topology-aware Embedding Memory (TEM) significantly outperform state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-01-24T03:03:17Z)
• Bayesian Recurrent Units and the Forward-Backward Algorithm [91.39701446828144]
  Using Bayes's theorem, we derive a unit-wise recurrence as well as a backward recursion similar to the forward-backward algorithm. The resulting Bayesian recurrent units can be integrated as recurrent neural networks within deep learning frameworks. Experiments on speech recognition indicate that adding the derived units at the end of state-of-the-art recurrent architectures can improve the performance at a very low cost in terms of trainable parameters.
  arXiv  Detail & Related papers  (2022-07-21T14:00:52Z)
• ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation [106.04777600352743]
  Differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory. The single-path DARTS comes in, which only chooses a single-path submodel at each step. While being memory-friendly, it also comes with low computational costs. We propose a new algorithm called RObustifying Memory-Efficient NAS (ROME) to give a cure.
  arXiv  Detail & Related papers  (2020-11-23T06:34:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.