Cooperative Phenomenon: Statistical Physics Origins of Connectionist Learning

Mehmet Süzen (1)

1 American Physical Society

A short account of origins of mathematical formalism of neural networks is presented for physicists and computer scientist in basic discrete mathematical setting informally. The discourse of the development of mathematical formalism on the dynamics of lattice models in statistical physics and learning internal representations of neural networks as discrete architectures as quantitative tools evolve in two almost distinct fields more than half a century with limited overlap. We aim at bridging the gap by claiming that the analogy between two approaches are not artificial but naturally occuring due to how modelling cooperative phenomenon is constructed. We define the Lenz-Ising architectures (ILAs) for this purpose.

Mots clés: Lenz-Ising Architectures; Statistics of Cooperative Phenomenon; Learning; Dynamics; Lattice Models; Spin-glasses; Neurophysiology; Statistical Physics; Neural Networks

Domaines: Mécanique statistique [cond-mat.stat-mech]

Mehmet Süzen. Cooperative Phenomenon: Statistical Physics Origins of Connectionist Learning. 2022. ⟨hal-03650339v2⟩