About this event
Recurrent Neural Networks (RNNs) represent the reference class of Deep Learning models for learning from sequential data. Despite the widespread success, a major downside of RNNs and commonly derived ‘gating’ variants (LSTM, GRU) is given by the high cost of the involved training algorithms. In this context, an increasingly popular alternative is the Reservoir Computing (RC) approach, which enables limiting the training algorithm to operate only on a restricted set of (output) parameters. RC is appealing for several reasons, including the amenability of being implemented in low-powerful edge devices, enabling adaptation and personalization in IoT and cyber-physical systems applications.
This webinar will introduce Reservoir Computing from scratch, covering all the fundamental design topics as well as good practices for real-world use cases. It is targeted to both researchers and practitioners that are interested in setting up fastly-trained Deep Learning models for sequential data.
Dr. Johannes Nagele is a trained physicist and computational neuroscientist. For almost a decade he studied the origin of life, in particular the functioning of the mammalian brain. Since joining [at] in 2020, he continues his AI journey and applies his research to add value to customer products.
Claudio Gallicchio is an Assistant Professor of Machine Learning at the Department of Computer Science of the University of Pisa, Italy. His research is based on the fusion of concepts from Deep Learning, Recurrent Neural Networks, and Randomized Neural Systems.
Als Data & AI Experten unterstützen wir Sie auf Ihrem Weg zur Digitalisierung. Gemeinsam generieren wir Mehrwerte aus Ihren Daten durch den Einsatz künstlicher Intelligenz.
Share this event