Developmental Symmetry-Loss: A Free-Energy Perspective on Brain-Inspired Invariance Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Size-regulated symmetry breaking in reaction-diffusion models of developmental transitions
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
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 AnalysisSGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training
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…
AttributeBrain development dictates energy constraints on neural architecture search: cross-disciplinary insights on optimization strategies
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 SearchNoether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks
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…