A highly parameterizable framework for Conditional Restricted Boltzmann Machine based workloads accelerated with FPGAs and OpenCL
URL: https://linkinghub.elsevier.com/retrieve/pii/S0167739X19313676
UPCommons Handle URL http://hdl.handle.net/2117/186484
Authors: Jakšić, Zoran / Cadenelli, Nicola / Prats, David / Polo, Jordà / Berral, Josep Lluis / Perez, David
Research Lines: Applied Learning Methods / Data-Center Optimization
Publication: Future Generation Computer Systems
Volume / Pagination: 104 / 201 - 211