Power/Performance Bits: April 16


Faster CNN training Researchers at North Carolina State University developed a technique that reduces training time for deep learning networks by more than 60% without sacrificing accuracy. Convolutional neural networks (CNN) divide images into blocks, which are then run through a series of computational filters. In training, this needs to be repeated for the thousands to millions of images... » read more

System Bits: Feb. 19


Eco-friendly material for wireless IoT sensors Researchers at Canada’s Simon Fraser University and in Switzerland collaborated on developing a wood-derived cellulose material that could be used in a 3D printer, instead of the customary plastic and polymeric materials for electronics. With 3D printing, the material can offer flexibility to add or embed functions onto 3D shapes or fabrics, the... » read more

System Bits: Sept. 11


Researchers ‘teleport’ a quantum gate In a key architectural step for building modular quantum computers, Yale University researchers have demonstrated the teleportation of a quantum gate between two qubits, on demand. [caption id="attachment_24137942" align="alignleft" width="300"] A network overview of the modular quantum architecture demonstrated in the new study.Source: Yale Universit... » read more