5 papers
Belief Graphs with Reasoning Zones: Structure, Dynamics, and Epistemic Activation
Saleh Nikooroo, Thomas Engel
Belief systems are rarely globally consistent, yet effective reasoning often persists locally. We propose a novel graph-theoretic framework that cleanly separates credibility--exte…
Understanding Learning Dynamics Through Structured Representations
Saleh Nikooroo, Thomas Engel
While modern deep networks have demonstrated remarkable versatility, their training dynamics remain poorly understood--often driven more by empirical tweaks than architectural insi…
Cross-Model Semantics in Representation Learning
Saleh Nikooroo, Thomas Engel
The internal representations learned by deep networks are often sensitive to architecture-specific choices, raising questions about the stability, alignment, and transferability of…
Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria
Saleh Nikooroo, Thomas Engel
This paper outlines a general formal framework for reasoning systems, intended to support future analysis of inference architectures across domains. We model reasoning systems as s…
Structured Transformations for Stable and Interpretable Neural Computation
Saleh Nikooroo, Thomas Engel
Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introd…