CEA-Leti takes inspiration from cutting-edge AI in the insect nervous system

We’re excited to bring back Transform 2022 in person on July 19 and virtually from July 20-28. Join leaders in AI and data for in-depth discussions and exciting networking opportunities. Register today!

CEA-Leti, a French research institute, has received a $3 million grant from the European Research Council (ERC) to build a cutting-edge intelligent AI system inspired by the nervous system of the insect. The nanoscale system uses new technologies to improve the performance and power efficiency of cutting-edge AI. Targeted applications include robotics, such as fruit picking and rescuing, medical implants and wearable electronics.

Although the classic computing architectures used in electronics like the PC, data center and mobile devices are ubiquitous today, the problem is that most of the energy is actually used to move the data rather than to process them. This is why researchers over time have tried to find more optimal approaches, especially given the rise of AI over the past decade. One such alternative is called in-memory computing, where memory is used for both storage and processing.

Buggy inspiration for advanced AI

However, the problem with in-memory computing is that it requires fast, nonvolatile, high-endurance memory. Such memory does not currently exist, because DRAM is volatile. To circumvent this problem and reduce memory requirements, CEA-Leti scientists took inspiration from the nervous system of insects.

Principal Scientist Elisa Vianello has received a $3 million grant from the ERC to use novel nanoscale memory technologies that mimic the biological mechanisms of insects to create silicon-based, energy-efficient nanoscale systems. energy for advanced AI.

“My project is to take inspiration from insect nervous systems to relax hardware requirements for memory density and reliability, and to build the new nanosystems we need to enable learning from a very large volume. limited noisy data,” Vianello said.

“Crickets make precise decisions based on slow, imprecise and unreliable neurons and synapses in order to escape their predators. By closely examining their biology, we have identified a diversity of memory-like functions at play in their systems sensory and nervous.By combining these different functions, cricket’s internal computer system achieves astonishing performance and energy efficiency.

The main objective is to create devices that allow learning from a limited amount of noisy data. This data could come from sensors such as video cameras, radar, ECG, EMG, bio-impedance flow, and brain signals. To do this, Vianello discovered that various functions of the insect’s nervous system closely resemble those of the various memory technologies that CEA-Leti is working on. Thus, scientists aim to create a “hybrid synapse” that co-integrates these different memory technologies.

The concept of a heterogeneous distributed computing system shows various processing units and sensors that are connected through spiked and spikeless links.

VentureBeat’s mission is to be a digital public square for technical decision makers to learn about transformative enterprise technology and conduct transactions. Learn more about membership.