East Tennessee State University
Grokking Applied to Chaotic Iterates of the Logistic Map
Abstract
dc:description.abstractThis thesis investigates grokking, the delayed transition from memorization to generalization in neural networks trained on deterministic chaotic data. Using an integer–arithmetic discretization of the logistic map, yn+1 =( a yn(p − yn))/ p 2 , bounded aperiodic sequences were generated across control parameters α ranging from 3.0 to 4.0. Transformer-based models displayed characteristic grokking curves. In periodic and chaotic regimes, validation accuracy rose suddenly after long plateaus, while at the Feigenbaum boundary (α ≈ 3.57) generalization failed completely. Increasing data diversity restored learning in chaotic domains, and explicit α–conditioning enabled a single network to generalize across all regimes. A bifurcation diagram of model-predicted data reproduced the main features of the true logistic map, confirming that the network captured the underlying dynamics. These results link delayed generalization in deep learning to structural transitions in deterministic chaos.
Degree
thesis:*- Name thesis:degree_name
- MS (Master of Science)
- Level thesis:degree_level
- Thesis - unrestricted
- Discipline thesis:degree_discipline
- Mathematical Sciences
- Grantor dc:publisher
- East Tennessee State University
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Donkoh, Felix
Subjects
dc:subject × 8Rights
dc:rights- Statement dc:rights
-
- Copyright by the authors.
- Language dc:language
- eng
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://dc.etsu.edu/etd/4613