[PDG 486] Online Continual Learning on Intel Loihi 2 via a Co-designed SNN

Link to article: https://arxiv.org/pdf/2511.01553
Title: Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network
Content: CLP-SNN is a spiking neural network for edge-device continual learning that adapts to new, non-stationary data without rehearsal or catastrophic forgetting, using a local self-normalizing learning rule and an autonomous spike-driven state machine on Intel Loihi 2. It matches replay-based few-shot accuracy on OpenLORIS while dramatically outperforming an edge-GPU baseline in efficiency, achieving 113× lower latency and 6,600× lower energy through algorithmic gains plus neuromorphic hardware co-design.
Slack link: ml-ka.slack.com, channel: #pdg. Please join us -- if you cannot join, please message us here or to mlpaperdiscussiongroupka@gmail.com.

In the Paper Discussion Group (PDG) we discuss recent and fundamental papers in the area of machine learning on a weekly basis. If you are interested, please read the paper beforehand and join us for the discussion. If you have not fully understood the paper, you can still participate – everyone is welcome! You can join the discussion or simply listen in. The discussion is in German or English depending on the participants.