Mechanistic Interpretability of Fine-Tuned Vision Transformers on Distorted Images: Decoding Attention Head Behavior for Transparent and Trustworthy AI

Documenti analoghi

• Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching
  di: Bahador, Nooshin
  Pubblicazione: (2025)
• Chirp Localization via Fine-Tuned Transformer Model: A Proof-of-Concept Study
  di: Bahador, Nooshin, et al.
  Pubblicazione: (2025)
• Semi-Supervised Anomaly Detection Pipeline for SOZ Localization Using Ictal-Related Chirp
  di: Bahador, Nooshin, et al.
  Pubblicazione: (2025)
• Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept Framework
  di: Bahador, Nooshin
  Pubblicazione: (2025)
• Vision Transformers Exhibit Human-Like Biases: Evidence of Orientation and Color Selectivity, Categorical Perception, and Phase Transitions
  di: Bahador, Nooshin
  Pubblicazione: (2025)