7 papers
Uncertainty-Aware Post-Hoc Calibration: Mitigating Confidently Incorrect Predictions Beyond Calibration Metrics
Hassan Gharoun, Mohammad Sadegh Khorshidi, Kasra Ranjbarigderi +2
Despite extensive research on neural network calibration, existing methods typically apply global transformations that treat all predictions uniformly, overlooking the heterogeneou…
Beyond Uncertainty Quantification: Learning Uncertainty for Trust-Informed Neural Network Decisions - A Case Study in COVID-19 Classification
Hassan Gharoun, Mohammad Sadegh Khorshidi, Fang Chen +1
Reliable uncertainty quantification is critical in high-stakes applications, such as medical diagnosis, where confidently incorrect predictions can erode trust in automated decisio…
Domain-Informed Genetic Superposition Programming: A Case Study on SFRC Beams
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun +3
This study presents domain-informed genetic superposition programming (DIGSP), a symbolic regression framework tailored for engineering systems governed by separable physical mecha…
From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun +3
We study symbolic surrogate modeling of frozen Transformer embeddings to obtain compact, auditable classifiers with calibrated probabilities. For five benchmarks (SST2G, 20NG, MNIS…
Multi-population Ensemble Genetic Programming via Cooperative Coevolution and Multi-view Learning for Classification
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun +3
This paper introduces Multi-population Ensemble Genetic Programming (MEGP), a computational intelligence framework that integrates cooperative coevolution and the multiview learnin…
Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks
Hassan Gharoun, Mohammad Sadegh Khorshidi, Kasra Ranjbarigderi +2
This work proposes an evidence-retrieval mechanism for uncertainty-aware decision-making that replaces a single global cutoff with an evidence-conditioned, instance-adaptive criter…