An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictions

no code implementations • 7 Oct 2021 • Afshar Shamsi, Hamzeh Asgharnezhad, AmirReza Tajally, Saeid Nahavandi, Henry Leung

Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result.

Uncertainty Quantification

Uncertainty-Aware Credit Card Fraud Detection Using Deep Learning

no code implementations • 28 Jul 2021 • Maryam Habibpour, Hassan Gharoun, Mohammadreza Mehdipour, AmirReza Tajally, Hamzeh Asgharnezhad, Afshar Shamsi, Abbas Khosravi, Miadreza Shafie-khah, Saeid Nahavandi, Joao P. S. Catalao

Countless research works of deep neural networks (DNNs) in the task of credit card fraud detection have focused on improving the accuracy of point predictions and mitigating unwanted biases by building different network architectures or learning models.

Fraud Detection Uncertainty Quantification

An Uncertainty-Aware Deep Learning Framework for Defect Detection in Casting Products

no code implementations • 24 Jul 2021 • Maryam Habibpour, Hassan Gharoun, AmirReza Tajally, Afshar Shamsi, Hamzeh Asgharnezhad, Abbas Khosravi, Saeid Nahavandi

Secondly, to achieve a reliable classification and to measure epistemic uncertainty, we employ an uncertainty quantification (UQ) technique (ensemble of MLP models) using features extracted from four pre-trained CNNs.

Defect Detection Image Classification +2

Confidence Aware Neural Networks for Skin Cancer Detection

no code implementations • 19 Jul 2021 • Donya Khaledyan, AmirReza Tajally, Ali Sarkhosh, Afshar Shamsi, Hamzeh Asgharnezhad, Abbas Khosravi, Saeid Nahavandi

Deep learning (DL) models have received particular attention in medical imaging due to their promising pattern recognition capabilities.

Transfer Learning