ICONS CONFERENCE

International Conference on Neuromorphic Systems

ICONS 2021 will be held as a virtual conference. The meeting will take place July 27-29, 2021, with some live content, including presentations and networking opportunities, and some recorded presentations.

The goal of this conference is to bring together leading researchers in neuromorphic computing to present new research, develop new collaborations, and provide a forum to publish work in this area. Our focus will be on architectures, models, and applications of neuromorphic systems.

Yole Développement will participate in the following:

Adrien Sanchez, Technology & Market Analyst, Computing & Software

“Today Artificial Intelligence is transforming a big part of the tech and semiconductor industry. Every player has a strategy to use AI to do more and be smarter. Deep Learning is the predominant technology underpinning it, leveraging bigger and bigger neural networks which require a vast amount of data to train them offline. The computing resources and associated power consumption required for both training and inferences are ever-increasing and do not fit well in a world where power efficiency is a growing necessity. Today accelerators or even units within chips are dedicated to run efficiently the mathematical operations required. This improves the performance but does not change the size of the network, the amount of data needed, and, more generally, the brute force logic which is necessary.
Deep Learning will continue to follow a bright road for its part of the AI applications, but a new paradigm will be required to bring AI to edge devices, such as all-battery-power devices. There is currently a growing demand for a technology that will bring top-level AI to the edge, with low power consumption, low latency, and the ability to adapt to its environment with little data. Neuromorphic computing, a solution that draws inspiration from what happens in the brain, has these key specificities. At Yole Développement, we believe it could be the technology to enable the distributed edge AI revolution. In this presentation, we will focus on neuromorphic computing technology, trends, and applications.”