CEA-Leta finds inspiration for edge AI in insect nervous systems

We’re excited to bring Transform 2022 back in person on July 19 and virtually July 20 – August 3. Join AI and data leaders for insightful conversations and exciting networking opportunities. Learn more about Transform 2022

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

While classic computer architectures such as those used in electronics such as the PC, data center and mobile devices are ubiquitous today, one problem is that most of the energy is actually used moving data rather than processing data. That’s why researchers have tried to find more optimal approaches over time, 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 edge AI

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

Senior 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 for edge AI.

“My project is to draw inspiration from insect nervous systems to reduce hardware requirements in terms of memory density and reliability, and to build the new nanosystems we need to learn from a very limited amount of noise data,” said Vianello.

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

The primary goal is to create devices that allow learning from a limited amount of noisy data. Such data can come from sensors such as video cameras, radar, ECG, EMG, bioimpedance currents and brain signals. To that end, Vianello has discovered that several functions of the insect’s nervous system are very similar to those of various memory technologies that CEA-Leti is working on. Therefore, the scientists want to create a “hybrid synapse” that co-integrates these different memory technologies.

The concept of a heterogeneously distributed computing system shows different processing units and sensors connected through both continuous and non-continuous connections.

VentureBeat’s mission is to be a digital city square for tech decision makers to learn about transformative business technology and transactions. Learn more about membership.

This post CEA-Leta finds inspiration for edge AI in insect nervous systems

was original published at “https://venturebeat.com/2022/03/30/cea-leta-finds-inspiration-in-insects-nervous-systems-for-edge-ai/”