5 papers
On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and Adversarial Robustness
Ashkan Soleymani, Reyhaneh Hosseinpourkhoshkbari, Hadi Daneshmand +1
Can a network look stable at every layer and still be exponentially unstable as a whole? The Lipschitz constant of a neural network is a basic stability quantity appearing in optim…
Can You Spot the Virtual Patient (VP)? Expert Evaluation, Turing Test, Linguistic Analysis, and Semantic Similarity Analysis
Reyhaneh Hosseinpourkhoshkbari, Wei-chen Huang, Suvel Muttreja +1
Communication is a core clinical competency and essential for safe, effective patient care. Virtual patients (VPs) powered by large language models (LLMs) offer a promising alterna…
Human-Likeness is Multi-Dimensional: Evaluating LLM Generated Virtual Patients Against Simulated Patient Dialogue
Reyhaneh Hosseinpourkhoshkbari, Wei-Chen Huang, Yile Wang +3
Large language models (LLMs) are increasingly used to generate virtual patients (VPs) for medical training. As these systems move toward broader deployment in medical education, re…
Detection of Cognitive Diagnostic Model Misspecification using New Lancaster-Chesher Information Matrix Tests
Richard M. Golden, Reyhaneh Hosseinpourkhoshkbari
Model specification tests play a crucial role in evaluating the appropriateness of probability models for estimation and inference. Existing methods for the detection of model miss…
Assessment of Misspecification in CDMs Using a Generalized Information Matrix Test
Reyhaneh Hosseinpourkhoshkbari, Richard M. Golden
If the probability model is correctly specified, then we can estimate the covariance matrix of the asymptotic maximum likelihood estimate distribution using either the first or sec…