University of Ottawa researchers say brain-inspired chips could make data centers greener

The team mapped years of advances in electronic materials, device physics and circuit integration to identify the most promising artificial‑neuron designs. Professor Kim says these neuromorphic circuits could overcome the “memory wall” bottleneck that wastes energy when data moves between memory and processors. While the review, published in Advanced Functional Materials, focuses on large‑scale data‑center workloads, the authors note the same low‑power hardware could enable ultra‑thin wearables and other personal devices, potentially expanding the impact of greener AI computing.