Towards Human-Like Predictor with Rejection Option
Supervision: Prof. Dr. Nassir Navab,
Dr. Seong Tae Kim
Abstract
Recently, measuring statistical uncertainties in deep neural networks has been an important issue in various safe-critical applications such as autonomous driving, computer-aided diagnosis. However, training the predictor which has a rejection option without performance degradation is still an unsolved problem. In this project, we will investigate a novel method (i.e. human-like predictor) where the neural network could reject uncertain samples. The main goal of human-like predictor is to learn deep neural networks which know what they can do and cannot do. It would be important to calibrate the uncertainty of prediction while maintaining accuracy.
Requirements:
- Good understanding of statistics and machine learning methods.
- Very good programming skills in Python & TensorFlow? / PyTorch?
Location: