Research Bits: Sept. 2


Microwave neural network Researchers from Cornell University designed an on-chip microwave neural network that can perform real-time frequency domain computation for tasks like radio signal decoding, radar target tracking, and digital data processing. By using interconnected modes produced in tunable waveguides, the device can handle data streams in the tens of gigahertz while consuming less t... » read more

Research Bits: Sept. 9


All-silicon polarization multiplexer Researchers from the University of Adelaide and Osaka University propose an ultra-wideband integrated terahertz polarization (de)multiplexer implemented on a substrateless silicon base, which they tested in the sub-terahertz J-band (220-330 GHz) for 6G communications. “Our proposed polarization multiplexer will allow multiple data streams to be transmi... » read more

Chip Industry Technical Paper Roundup: April 2


New technical papers recently added to Semiconductor Engineering’s library. [table id=211 /] Find last week’s technical paper additions here. » read more

HW Implementation of Memristive ANNs


A new technical paper titled "Hardware implementation of memristor-based artificial neural networks" was published by KAUST, Universitat Autònoma de Barcelona, IBM Research, USC, University of Michigan and others. Abstract: "Artificial Intelligence (AI) is currently experiencing a bloom driven by deep learning (DL) techniques, which rely on networks of connected simple computing units oper... » read more

Research Bits: October 31


Skinlike sensor for robots University of British Columbia engineers with help from researchers from Frontier Robotics, Honda research institute, created a soft sensor that approximates skin. Mostly made of silicone rubber, the sensor uses weak electric fields to sense objects, even at a distance, and can detect forces into and along its surface. The sensor could provide touch sensitivity and d... » read more