Weebit ReRAM: Neuromorphic Demo |
![]() |
Weebit is a developer of innovative resistive RAM, also called as RRAM, or ReRAM technology, an emerging semiconductor memory targeting the growing number of applications where embedded flash is no longer feasible.
Here we demonstrate how our RRAM can provide an exciting new solution for artificial intelligence applications using spiking neural networks. Commonly today, neural networks are simulated using traditional digital processors and accelerators, but this is inefficient and power hungry. That’s why a growing number of companies and research institutes around the globe are focusing efforts on neuromorphic computing, which makes it possible to basically emulate the brain’s natural operation. This emulation is much more efficient than today’s simulations, consuming orders of magnitude less power, to allow sophisticated AI at a fraction of the power consumed by today’s systems. Because a ReRAM (RRAM) cell has physical and functional similarities to a biological brain synapse, it’s a natural candidate for implementing neuromorphic computing. Today, in this demo that we created with our R&D partner CEA-Leti, we’re showing spiking neural networks running on ReRAM cells. To learn more about Weebit ReRAM and the progress we are making with neuromorphic computing, visit our website – www.weebit-nano.com |