3 accepted papers
Unlike their biological counterparts, simple artificial neural networks are unable to retain information from their past state to influence their behavior. In this contribution, we propose to consider new nonlinear activation functions, whose outputs depend both from the current and past inputs thro…
This paper presents a new scheme to perform the canonical polyadic decomposition (CPD) of a symmetric tensor. We first formulate the CPD problem as a truncated moment problem, where a measure has to be recovered knowing some of its moments. The support of the measure is discrete and encodes the CPD.…
For dealing with sparse models, a large number of continuous approximations of the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> penalization have been proposed. However, the most accurate ones lead to non-convex opti-mization problems. In t…