Safety-Relevant AI-Based System Robustification with Neural Network Ensembles

Adrià Aldomà, Axel Brando, Francisco J. Cazorla, Jaume Abella

Abstract: Functional safety requirements of AI-based safety critical applications challenge AI models, whose accuracy can be limited. In this paper, we show how using several cooperative deep learning (DL) models helps to raise global accuracy and reject making a prediction when confidence is below a pre-established threshold.