minAction.net: Energy-First Neural Architecture Design -- From Biological Principles to Systematic Validation

• URL: http://arxiv.org/abs/2604.24805v2
• Date: Wed, 29 Apr 2026 19:07:35 GMT
• Title: minAction.net: Energy-First Neural Architecture Design -- From Biological Principles to Systematic Validation
• Abstract summary: Modern learning optimize for accuracy without explicit treatment of internal computational cost.<n>We evaluate energy-aware learning across 2203 experiments spanning vision, text neuromorphic, and physiological datasets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Modern machine learning optimizes for accuracy without explicit treatment of internal computational cost, even though physical and biological systems operate under intrinsic energy constraints. We evaluate energy-aware learning across 2,203 experiments spanning vision, text, neuromorphic, and physiological datasets with 10 seeds per configuration and factorial statistical analysis. Three findings emerge. First, architecture alone explains negligible variance in accuracy (partial eta^2 = 0.001), while the architecture x dataset interaction is large (partial eta^2 = 0.44, p < 0.001), demonstrating that optimal architecture depends critically on task modality and rejecting the assumption of a universal best architecture. Second, a controlled lambda-sweep across lambda in {0, 1e-5, 1e-4, 1e-3, 1e-2} validates a single-parameter energy-regularized objective L = L_CE + lambda * E(theta, x): across this range, internal activation energy decreases by approximately three orders of magnitude relative to the unregularized lambda=0 baseline, with negligible accuracy change (<0.5 percentage points) on both MNIST and Fashion-MNIST. Third, energy-first architectures inspired by an action-principle framework yield 5-33% within-modality training-efficiency gains over conventional baselines. These results emerge from a research program that interprets learning through a structural correspondence between the action functional in classical mechanics, free energy in statistical physics, and KL-regularized objectives in variational inference. We frame this correspondence as a design hypothesis, not a derivation.

Related papers

• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• Leveraging Energy Features for Surface Classification with Deep Learning: A Comparative Analysis Across Three Independent Datasets [45.88028371034407]
  The energy-based method remains a comparatively underexamined approach for surface classification in mobile robotics.<n>This study evaluated the viability of using energy-derived features as either a standalone classification modality or as supplementary input to inertial data.
  arXiv  Detail & Related papers  (2026-06-17T05:24:32Z)
• From Phenomenological Fitting to Endogenous Deduction: A Paradigm Leap via Meta-Principle Physics Architecture [0.0]
  We construct the Meta-Principle Physics Architecture (MPPA)<n>MPPA embeds three core meta-principles - Connectivity, Conservation, Periodicity - into its architecture.<n> Experiments show MPPA 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)
  arXiv  Detail & Related papers  (2026-04-09T13:35:17Z)
• Comparing Physics-Informed and Neural ODE Approaches for Modeling Nonlinear Biological Systems: A Case Study Based on the Morris-Lecar Model [0.0]
  This study systematically evaluates the performance of PINNs and NODEs across three canonical bifurcation regimes.<n>Results indicate that PINNs tend to achieve higher accuracy and robustness in scenarios involving stiffness or sensitive bifurcations.
  arXiv  Detail & Related papers  (2026-03-27T18:53:53Z)
• Neuro-Symbolic Activation Discovery: Transferring Mathematical Structures from Physics to Ecology for Parameter-Efficient Neural Networks [0.0]
  We propose Neuro-Symbolic Activation Discovery, a framework that uses Genetic Programming to extract interpretable mathematical formulas from data.<n>Our key contribution is the discovery of a Geometric Transfer phenomenon: activation functions learned from particle physics data successfully generalize to ecological classification.<n>Our work opens pathways toward domain-specific activation libraries for efficient scientific machine learning.
  arXiv  Detail & Related papers  (2026-01-10T02:49:32Z)
• Phythesis: Physics-Guided Evolutionary Scene Synthesis for Energy-Efficient Data Center Design via LLMs [9.210347753567092]
  Data center infrastructure serves as the backbone to support the escalating demand for computing capacity.<n>Traditional design methodologies blend human expertise with specialized simulation tools.<n>Recent studies adopt generative artificial intelligence to design plausible human-centric indoor layouts.<n>We propose Phythesis, a novel framework that synergizes large language models (LLMs) and physics-guided evolutionary optimization.
  arXiv  Detail & Related papers  (2025-12-11T13:04:44Z)
• Teaching Language Models to Reason with Tools [73.21700643314917]
  We present emphHint-Engineering, a new data synthesis strategy that strategically injects diverse hints at optimal points within reasoning paths.<n>CoRT significantly enhances efficiency, reducing token usage by approximately 30% for the 32B model and 50% for the 1.5B model.
  arXiv  Detail & Related papers  (2025-10-23T08:41:44Z)
• Physics-Inspired All-Pair Interaction Learning for 3D Dynamics Modeling [28.23126775948343]
  We propose PAINET, a principled SE(3)-equivariant neural architecture for learning all-pair interactions in multi-body systems.<n>We show that PAINET consistently outperforms recently proposed models, yielding 4.7% to 41.5% error reductions in 3D dynamics prediction with comparable computation costs in terms of time and memory.
  arXiv  Detail & Related papers  (2025-10-05T14:48:26Z)
• A Neural Network for the Identical Kuramoto Equation: Architectural Considerations and Performance Evaluation [0.0]
  We investigate the efficiency of Deep Neural Networks (DNNs) to approximate the solution of a nonlocal conservation law derived from the identical-oscillator Kuramoto model.<n>Through systematic experimentation, we demonstrate that network configuration parameters influence convergence characteristics.<n>We identify fundamental limitations of standard feed-forward architectures when handling singular or piecewise-constant solutions.
  arXiv  Detail & Related papers  (2025-09-17T19:37:01Z)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• DimINO: Dimension-Informed Neural Operator Learning [41.37905663176428]
  DimINO is a framework inspired by dimensional analysis.<n>It can be seamlessly integrated into existing neural operator architectures.<n>It achieves up to 76.3% performance gain on PDE datasets.
  arXiv  Detail & Related papers  (2024-10-08T10:48:50Z)
• Efficient Materials Informatics between Rockets and Electrons [0.0]
  This dissertation focuses on the design of functionally graded materials (FGMs) incorporating ultra-high temperature refractory high entropy alloys (RHEAs) At the atomistic level, a data ecosystem optimized for machine learning (ML) from over 4.5 million relaxed structures, called MPDD, is used to inform experimental observations and improve thermodynamic models. The resulting multi-level discovery infrastructure is highly generalizable as it focuses on encoding problems to solve them easily rather than looking for an existing solution.
  arXiv  Detail & Related papers  (2024-07-05T17:03:26Z)
• Energy Transformer [64.22957136952725]
  Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory. We propose a novel architecture, called the Energy Transformer (or ET for short), that uses a sequence of attention layers that are purposely designed to minimize a specifically engineered energy function.
  arXiv  Detail & Related papers  (2023-02-14T18:51:22Z)
• Learning Physical Dynamics with Subequivariant Graph Neural Networks [99.41677381754678]
  Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization. Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall.
  arXiv  Detail & Related papers  (2022-10-13T10:00:30Z)
• eQE 2.0: Subsystem DFT Beyond GGA Functionals [58.720142291102135]
  subsystem-DFT (sDFT) can dramatically reduce the computational cost of large-scale electronic structure calculations. The key ingredients of sDFT are the nonadditive kinetic energy and exchange-correlation functionals which dominate it's accuracy. eQE 2.0 delivers excellent interaction energies compared to conventional Kohn-Sham DFT and CCSD(T)
  arXiv  Detail & Related papers  (2021-03-12T22:26:36Z)

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.