AI is not needed everywhere… but wherever it is needed to improve people’s lives, we try to make it interactive, energy-efficient and sustainable. To do so, we take inspiration from the natural intelligence in biological brains. We explore neuromorphic computing hardware and algorithms that only sense and process changes in the environment in a fast, efficient and adaptive way.

I’m Lyes Khacef, senior research scientist in neuromorphic computing at Sony. I am trying to understand the computational principles of the brain to get some inspiration for the modeling and hardware implementation of self-organizing neural networks. The main question is: What is the right level of abstraction from biology to get the best performance in artificial systems? 

One of the fundamental computational paradigms from biology is to use local plasticity mechanisms that solve the latency and energy-efficiency constraints of online learning, in contrast with recent developments of deep learning. The global behavior of these networks emerges from local interactions without a global controller or external supervisor, and can solve complex tasks such as multimodal classification. I think that this self-organizing property is a key feature that leads to fast, efficient and adaptive systems. It also leads to hard headaches sometimes... but I believe it's worth it.