[A]rtificial intelligence systems could truly become more like human brains, and some researchers believe they know how: AI design must be elevated to another dimension—literally. While current models have certain parameters of width and depth already, AI can be refashioned to have an additional, structured complexity researchers are calling the “height” dimension.
AI models already have width, the number of nodes in a layer. … There’s also depth, the number of layers in a network. … When you add height, as internal wiring or shortcuts within a layer, it creates “richer interactions among neurons without increasing depth or width. It reflects how local neural circuits in the brain … interact to improve information processing,” [writes Dr. Ge Wang, co-author of a new AI study.]
“Together, they help networks evolve over time and settle into stable, meaningful patterns, like how your brain can recognize a face even from a blurry image,” Wang says. “These structures enrich AI’s ability to refine decisions over time, just like the brain’s iterative reasoning.”
