Neural Architecture Search with In‐Memory Multiply–Accumulate and In‐Memory Rank Based on Coating Layer Optimized C‐Doped Ge₂Sb₂Te₅ Phase Change Memory (Adv. Funct. Mater. 15/2024)

Neural Architecture Search Neural architecture search (NAS) can design neural network models with better performance than manual design. However, the energy and time consumption of conventional software-based NAS are huge, hindering its development and applications. In article number 2300458, Zhitang Song, Yuchao Yang, Ru Huang, and co-workers report 4 Mb PCM chips that enable in-memory MAC and in-memory rank for efficient NAS. The PCM-based NAS improves the energy and time efficiency by 4779× and 123× compared with GPU.