7 papers
Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept Framework
Nooshin Bahador
This article presents a modular, component-based architecture for developing and evaluating AI agents that bridge the gap between natural language interfaces and complex enterprise…
Classifying Clinical Outcome of Epilepsy Patients with Ictal Chirp Embeddings
Nooshin Bahador, Milad Lankarany
This study presents a pipeline leveraging t-Distributed Stochastic Neighbor Embedding (t-SNE) for interpretable visualizations of chirp features across diverse outcome scenarios. T…
Semi-Supervised Anomaly Detection Pipeline for SOZ Localization Using Ictal-Related Chirp
Nooshin Bahador, Milad Lankarany
This study presents a quantitative framework for evaluating the spatial concordance between clinically defined seizure onset zones (SOZs) and statistically anomalous channels ident…
Vision Transformers Exhibit Human-Like Biases: Evidence of Orientation and Color Selectivity, Categorical Perception, and Phase Transitions
Nooshin Bahador
This study explored whether Vision Transformers (ViTs) developed orientation and color biases similar to those observed in the human brain. Using synthetic datasets with controlled…
Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching
Nooshin Bahador
This study investigates the localization of knowledge representation in fine-tuned GPT-2 models using Causal Layer Attribution via Activation Patching (CLAP), a method that identif…
Chirp Localization via Fine-Tuned Transformer Model: A Proof-of-Concept Study
Nooshin Bahador, Milad Lankarany
Spectrograms are pivotal in time-frequency signal analysis, widely used in audio processing and computational neuroscience. Chirp-like patterns in electroencephalogram (EEG) spectr…