From Phenomenological Fitting to Endogenous Deduction: A Paradigm Leap via Meta-Principle Physics Architecture
2026-04-09 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors propose a new neural network design called Meta-Principle Physics Architecture (MPPA) that integrates basic physical concepts directly into the model. Instead of just learning patterns from data, MPPA includes principles like connectivity, conservation, and periodicity through specialized components. Their experiments show that MPPA improves performance on physical reasoning, math, and logic tasks and generalizes better to new situations with only a small increase in model size. This approach aims to help AI understand physical rules, not just statistical correlations.
Neural Network ArchitecturePhenomenological FittingConnectivityConservationPeriodicityCausal AttentionFFT (Fast Fourier Transform)Energy TrackingPhysical ReasoningOut-of-Distribution Generalization
Authors
Helong Hu, HongDan Pan, ShuiQing Hu
Abstract
The essence of current neural network architectures is phenomenological fitting: they learn input-output statistical correlations via massive parameters and data, yet lack intrinsic understanding of the fundamental principles governing physical reality. This paper proposes a paradigm leap from pure phenomenological fitting to the fusion of phenomenological fitting and endogenous deduction. By embedding physical meta-principles into neural network architecture, we construct the Meta-Principle Physics Architecture (MPPA). Specifically, MPPA embeds three core meta-principles - Connectivity, Conservation, Periodicity - into its architecture, implemented via three core components: the Gravitator realizes Connectivity via standard causal attention; the Energy Encoder implements Conservation via log-domain energy tracking and delayed compensation; the Periodicity Encoder fulfills Periodicity via FFT-based spectral analysis and delayed modulation. These components collaborate via a learnable independent gating fusion mechanism, forming a complete physical cognition framework of 'local relational connectivity - global conservation constraint - evolutionary periodic law'. Experiments show MPPA achieves significant improvements: physical reasoning (from near zero to 0.436, 0.436 vs 0.000), 2.18x mathematical task improvement (0.330 vs 0.151), 52% logical task gain (0.456 vs 0.300), and 3.69% lower validation perplexity (259.45 vs 269.40), with only 11.8% more parameters (242.40M vs 216.91M). Notably, MPPA shows strong generalization on out-of-distribution physical scenarios, proving the robustness and interpretability of this principle-embedded design. This work establishes a new theoretical foundation and technical path for next-generation AI with physical common sense, causal reasoning, and mathematical rigor.