Artificial intelligence has traditionally been derived from human brain dynamics. However, deep learning has several important limitations as compared to brain learning. Researchers from Bar-Ilan University in Israel have solved the puzzle of how the brain, with its limited realization of precise mathematical operations, can compete with advanced artificial intelligence systems implemented on fast and parallel computers. This discovery of efficient dendritic tree learning for AI inspired by brain dynamics can achieve better classification success rates than previously achieved by deep learning architectures. This finding paves the way for efficient, biologically-inspired new AI hardware and algorithms. The emergence of a new hardware is required to efficiently imitate brain dynamics.
Today: December 10, 2023