Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Jianfeng, Li, Zeyan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914224526065664
author Xu, Jianfeng
Li, Zeyan
author_facet Xu, Jianfeng
Li, Zeyan
contents The rapid scaling of artificial intelligence models has revealed a fundamental tension between model capacity (storage) and inference efficiency (computation). While classical information theory focuses on transmission and storage limits, it lacks a unified physical framework to quantify the thermodynamic costs of generating information from compressed laws versus retrieving it from memory. In this paper, we propose a theoretical framework that treats information processing as an enabling mapping from ontological states to carrier states. We introduce a novel metric, Derivation Entropy, which quantifies the effective work required to compute a target state from a given logical depth. By analyzing the interplay between Shannon entropy (storage) and computational complexity (time/energy), we demonstrate the existence of a critical phase transition point. Below this threshold, memory retrieval is thermodynamically favorable; above it, generative computation becomes the optimal strategy. This "Energy-Time-Space" conservation law provides a physical explanation for the efficiency of generative models and offers a rigorous mathematical bound for designing next-generation, energy-efficient AI architectures. Our findings suggest that the minimization of Derivation Entropy is a governing principle for the evolution of both biological and artificial intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19156
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints
Xu, Jianfeng
Li, Zeyan
Information Theory
Artificial Intelligence
Logic in Computer Science
The rapid scaling of artificial intelligence models has revealed a fundamental tension between model capacity (storage) and inference efficiency (computation). While classical information theory focuses on transmission and storage limits, it lacks a unified physical framework to quantify the thermodynamic costs of generating information from compressed laws versus retrieving it from memory. In this paper, we propose a theoretical framework that treats information processing as an enabling mapping from ontological states to carrier states. We introduce a novel metric, Derivation Entropy, which quantifies the effective work required to compute a target state from a given logical depth. By analyzing the interplay between Shannon entropy (storage) and computational complexity (time/energy), we demonstrate the existence of a critical phase transition point. Below this threshold, memory retrieval is thermodynamically favorable; above it, generative computation becomes the optimal strategy. This "Energy-Time-Space" conservation law provides a physical explanation for the efficiency of generative models and offers a rigorous mathematical bound for designing next-generation, energy-efficient AI architectures. Our findings suggest that the minimization of Derivation Entropy is a governing principle for the evolution of both biological and artificial intelligence.
title Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints
topic Information Theory
Artificial Intelligence
Logic in Computer Science
url https://arxiv.org/abs/2511.19156