Talk on Thursday Sep 23, 2021 at 12:00 Place: Zoom Seminar Title: Deep Randomized Neural Networks Speaker: Claudio Gallicchio, University of Pisa, Italy Abstract: <p>Deep Neural Networks (DNNs) are a fundamental tool in the modern development of Machine Learning. Beyond the merits of the training algorithms, a great part of&nbsp;DNNs success is due to the inherent properties of their layered architectures, i.e., to the introduced architectural biases. This talk explores recent classes of DNN models in which&nbsp;the majority of connections are untrained, i.e., randomized or more generally fixed according to some specific heuristic.&nbsp;<br /> Limiting the training algorithms to operate on a reduced set of weights implies intriguing features. Among them, the extreme efficiency of the learning processes is undoubtedly a&nbsp;striking advantage with respect to fully trained counterparts. Besides, despite the involved simplifications, randomized neural systems possess remarkable properties both in&nbsp;practice, achieving state-of-the-art results in multiple domains, and theoretically, allowing us to analyze intrinsic properties of neural architectures.<br /> This talk will cover the major aspects regarding Deep Randomized Neural Networks, with a particular focus on Deep Reservoir Computers for time-series and graphs.</p> <p>&nbsp;</p> <p>Link Zoom:&nbsp;<a href="https://uibuniversitat.zoom.us/j/83043347066">https://uibuniversitat.zoom.us/j/83043347066</a></p>; Url event:https://ifisc.uib-csic.es/en/events/seminars/deep-randomized-neural-networks...