Author:

Keywords:

Science & Technology, Technology, Life Sciences & Biomedicine, Computer Science, Artificial Intelligence, Neurosciences, Computer Science, Neurosciences & Neurology, Credal sets, Classification, Probability intervals, Uncertainty estimation, Interval neural networks, QUANTIFICATION, Neural Networks, Computer, Uncertainty, Bayes Theorem, Algorithms, Probability, Humans, Artificial Intelligence & Image Processing, 4602 Artificial intelligence, 4611 Machine learning, 4905 Statistics

Abstract:

Effective uncertainty estimation is becoming increasingly attractive for enhancing the reliability of neural networks. This work presents a novel approach, termed Credal-Set Interval Neural Networks (CreINNs), for classification. CreINNs retain the fundamental structure of traditional Interval Neural Networks, capturing weight uncertainty through deterministic intervals. CreINNs are designed to predict an upper and a lower probability bound for each class, rather than a single probability value. The probability intervals can define a credal set, facilitating estimating different types of uncertainties associated with predictions. Experiments on standard multiclass and binary classification tasks demonstrate that the proposed CreINNs can achieve superior or comparable quality of uncertainty estimation compared to variational Bayesian Neural Networks (BNNs) and Deep Ensembles. Furthermore, CreINNs significantly reduce the computational complexity of variational BNNs during inference. Moreover, the effective uncertainty quantification of CreINNs is also verified when the input data are intervals.