Ferroelectric Memristors and Exotic Materials to Drive AI

EE Times Current · 12 Jan 2024 · 42m

What this episode covers

Professor Beatriz Noheda, director of the Groningen Cognitive Systems and Materials Center (CogniGron), explains how nanoscale ferroelectric materials like hafnium oxide can drive brain-inspired computing. She details the use of strain engineering to stabilize ferroelectric phases at the nanoscale and the potential for self-assembled memristive networks to emulate synaptic connections. The discussion also covers the challenges of characterizing evolving materials and the timeline for deploying these devices in neuromorphic chips.

Mentioned

Companies
Ramtron, Fujitsu, Phineon
Products
FRAM
Materials
Hafnium oxide
Also
CogniGron, Elizabeth Akika, Harvey Jager, Matthew Cook, Adrian Thompson, Hugo DeGaris, Sataru Nakasuji

Other shows on the same ground, closest first.

  • The Next Byte Podcast · 29m

    72. Spiderweb Inspired & Graphene Enhanced Microchips

    Hosts Daniel and Farbod discuss two breakthroughs in microchip technology: a graphene-hexagonal boron nitride (HBN) heterostructure developed by the University of Michigan and Ohio State University, and spiderweb-inspired vibrational microchips created by students at Delft University of Technology. They explain how the graphene-HBN stack enables deep UV LEDs and potentially quantum computing by overcoming silicon's thermal and physical limits, while the spiderweb geometry allows precision sensors to operate at room temperature by isolating thermal noise. The episode highlights the role of molecular beam epitaxy in material synthesis and Bayesian optimization in designing bio-inspired mechanical structures.

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by EE Times Current. The episode itself belongs to its publisher.