Multi-task learning (MTL) aims to improve the performance of multiple related tasks by exploiting the intrinsic relationships among them. Recently, multi-task feature learning alg...
Abstract This work introduces a self-supervised architecture for robust classification of moving obstacles in urban environments. Our approach presents a hierarchical scheme that r...
Roman Katz, Juan Nieto, Eduardo Mario Nebot, Bertr...
An approach to robust system level mixed signal design is presented based on analog platforms. The bottom-up characterization phase of platform components provides accurate perfor...
Fernando De Bernardinis, Pierluigi Nuzzo, Alberto ...
— The control approaches based on tasks, and particularly based on a hierarchy of tasks, enable to build complex behaviors with some nice properties of robustness and portability...
In this paper, we present a new and efficient method to implement robust smoothing of low-level signal features: B-spline channel smoothing. This method consists of three steps: en...