Skip to ContentSkip to Navigation
Research Zernike (ZIAM) News

Advent calendar - December 3rd - Dr. Lyes Khacef

03 December 2021

In the Zernike Institute Advent Calendar, we are presenting 24 short spotlights in December. In these specials, we highlight PhD students, postdocs, and technicians of our research groups - providing a glimpse into their typical day at work. In Episode 3 meet Dr. Lyes Khacef.

I imagine a world where intelligent artificial systems can learn from their experience to solve problems and empower people for the good of all mankind. That requires embedded systems that can learn online, efficiently and without supervision. This is why I'm inspired by the only known system which evolved to do it: our own brain.

Dr. Lyes Khacef
Dr. Lyes Khacef

I’m Lyes Khacef, postdoctoral researcher working on neuromorphic computing in the Bio-Inspired Circuits and Systems group led by Prof. Elisabetta Chicca. 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. One of the main insights from biology is to use local plasticity mechanisms that seem to be solving the latency and energy-efficiency constraints, in contrast with recent developments of deep learning. The global behavior of these networks emerge from local interactions without supervision, and can solve complex tasks such as multimodal classification. I think that this self-organizing property is a key feature that leads to efficient and adaptive systems. It also leads to hard headaches sometimes... but I believe it's worth it.

I spend most of my days reading about neuroscience, coding some learning algorithms and playing with neuromorphic hardware, in addition to supervising other projects. I love it, even if I miss organizing and traveling to conferences, and meeting more people physically. The physical meeting, that’s a key feature for our own self-organization, I think, to do more than the sum of our parts. It’s a bit difficult to come back to a normal life after Covid (if there ever was such a thing), mainly because I got used to working more than I should... I don’t know when to stop anymore. Luckily, our group is growing fast with people from all over the world, and they make sure that I don’t stay too long in the office (most of the time). I feel lucky to be here, to be part of the Zernike family, working on something I believe in and trying to find the right balance in my life. I don’t know if I’ll get there, but won’t stop trying.

Intel Loihi neuromorphic processor
Intel Loihi neuromorphic processor

Contact: Dr. Lyes Khacef

Last modified:01 December 2021 06.42 a.m.

More news