2026/07/21 by Hui Lin, Yukun Yang, Rong Zhao +2 · 3 voices
Computer Science · Engineering · #Advanced Memory and Neural Computing #Artificial neural network #Cognition #Core (optical fiber) #Energy consumption #Feature (linguistics) #Ferroelectric and Negative Capacitance Devices #Neural Networks and Reservoir Computing #Neuromorphic engineering #Plan (archaeology) #Porting
paper · pdf · doi:10.1038/s42256-026-01254-4
published in Nature Machine Intelligence 8(7), 1045-1065 (Nature Portfolio)
openalex publication_date 2026/07/21 · rss dc_date 2026/07/21 · openalex created_date 2026/07/22 · openalex updated_date 2026/08/01
Nature Machine Intelligence, Published online: 21 July 2026; doi:10.1038/s42256-026-01254-4 Lin et al. introduce a brain-inspired generative model that provides two key features of intelligence: planning and problem-solving. It uses cognitive maps, stochastic computing and compositional coding, and requires only local synaptic plasticity.