paper-with-me

홈 › Papers

Developmental Symmetry-Loss: A Free-Energy Perspective on Brain-Inspired Invariance Learning

2025-12-04 · Arif Dönmez arxiv

We propose Symmetry-Loss, a brain-inspired algorithmic principle that enforces invariance and equivariance through a differentiable constraint derived from environmental symmetries. The framework models learning as the iterative refinement of an effective symmetry group, paralleling developmental processes in which cortical representations align with the world's structure. By minimizing structural surprise, i.e. deviations from symmetry consistency, Symmetry-Loss operationalizes a Free-Energy--like objective for representation learning. This formulation bridges predictive-coding and group-theoretic perspectives, showing how efficient, stable, and compositional representations can emerge from symmetry-based self-organization. The result is a general computational mechanism linking developmental learning in the brain with principled representation learning in artificial systems.

📄 PDF Abstract BibTeX arXiv:2512.10984

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Size-regulated symmetry breaking in reaction-diffusion models of developmental transitions

2020-07-07 · Jake Cornwall Scoones, Deb Sankar Banerjee, Shiladitya Banerjee

The development of multicellular organisms proceeds through a series of morphogenetic and cell-state transitions, transforming homogeneous zygotes into complex adults by a process of self-organization. Many of these tran…

A Quantum Field Theory of Representation Learning

2019-07-04 · Robert Bamler, Stephan Mandt

Continuous symmetries and their breaking play a prominent role in contemporary physics. Effective low-energy field theories around symmetry breaking states explain diverse phenomena such as superconductivity, magnetism, …

Representation LearningTime SeriesTime Series Analysis

SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training

2025-05-29 · Ildus Sadrtdinov, Ivan Klimov, Ekaterina Lobacheva, Dmitry Vetrov

We present a thermodynamic interpretation of the stationary behavior of stochastic gradient descent (SGD) under fixed learning rates (LRs) in neural network training. We show that SGD implicitly minimizes a free energy f…

Attribute

Brain development dictates energy constraints on neural architecture search: cross-disciplinary insights on optimization strategies

2023-10-03 · Martin G. Frasch

Present day artificial neural architecture search (NAS) strategies are essentially prediction-error-optimized. That holds true for AI functions in general. From the developmental neuroscience perspective, I present evide…

Neural Architecture Search

Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks

2021-12-01 · NeurIPS 2021 12 · Hidenori Tanaka, Daniel Kunin

In nature, symmetry governs regularities, while symmetry breaking brings texture. In artificial neural networks, symmetry has been a central design principle to efficiently capture regularities in the world, but the role…