Incremental learning involves Machine Learning paradigms that dynamically adjust their previous knowledge whenever new training samples emerge. To address the problem of multi-task incremental learning without storing any samples of the previous tasks, the so-called Expert Gate paradigm was proposed, which consists of a Gate and a downstream network of task-specific CNNs, a.k.a. the Experts. The gate forwards the input to a certain expert, based on the decision made by a set of autoencoders. Unfortunately, as a CNN is intrinsically incapable of dealing with inputs of a class it was not specifically trained on, the activation of the wrong expert will invariably end into a classification error. To address this issue, we propose a probabilistic extension of the classic Expert Gate paradigm. Exploiting the prediction uncertainty estimations provided by Bayesian Convolutional Neural Networks (B-CNNs), the proposed paradigm is able to either reduce, or correct at a later stage, wrong decisions of the gate. The goodness of our approach is shown by experimental comparisons with state-of-the-art incremental learning methods.
A Bayesian approach to Expert Gate Incremental Learning / Mieuli, V.; Ponzio, F.; Mascolini, A.; Macii, E.; Ficarra, E.; Di Cataldo, S.. - 2021-:(2021), pp. 1-7. (Intervento presentato al convegno 2021 International Joint Conference on Neural Networks, IJCNN 2021 tenutosi a chn nel 18-22 July 2021) [10.1109/IJCNN52387.2021.9534204].