What has sparsity done for you lately? In this episode of Fish Fry, we investigate the challenges that surround on-device artificial intelligence processing. Megha Daga (Cadence Design Systems) and I discuss the why the presence of zeroes is becoming more and more important in the development of neural networks and how sparsity can be used for bandwidth and compute reduction. In this week’s News You May Have Missed, we check out how the the University of Adelaide is making huge strides in quantum memory technology with a little help from an atomic tractor beam and the world’s first “waveguide trap”.

Click here to download this episode

Links for November 9, 2018

Cadence Launches New Tensilica DNA 100 Processor IP Delivering Industry-Leading Performance and Power Efficiency for On-Device AI Applications

More information about how the University of Adelaide is trapping atoms, not spaceships, with tractor beams

High-Efficiency Cold-Atom Transport into a Waveguide Trap (Research paper)