The human brain is a dream for computer scientists: it has a huge computing power while consuming only a few tens of Watts. Imec researchers are combining state-of-the-art hardware and software to design chips that feature these desirable characteristics of a self-learning system.
Imec’s goal is to design the process technology and building blocks to make artificial intelligence to be energy efficient so that that it can be integrated into sensors. Such intelligent sensors will drive the internet of things forward. This would not only allow machine learning to be present in all sensors but also allow on-field learning capability to further improve the learning.
By co-optimizing the hardware and the software, the chip features machine learning and intelligence characteristics on a small area, while consuming only very little power. The chip is self-learning, meaning that is makes associations between what it has experienced and what it experiences. The more it experiences, the stronger the connections will be, as the researchers told. The latest chip has learned to compose new music and the rules for the composition are learnt on the fly.
“Because we have hardware, system design and software expertise under one roof, imec is ideally positioned to drive neuromorphic computing forward,” says Praveen Raghavan, distinguished member of the technical staff. “Our chip has evolved from co-optimizing logic, memory, algorithms and system in a holistic way. This way, we succeeded in developing the building blocks for such a self-learning system.”