Brain Inspired
Brain-inspired artificial intelligence (BIAI) seeks to improve AI systems by emulating the structure and function of the human brain. Current research focuses on developing neuromorphic hardware and algorithms, such as spiking neural networks (SNNs) and models incorporating principles like Hebbian learning, synaptic plasticity, and cortical architecture, to achieve more efficient, robust, and adaptable AI. This approach holds significant promise for advancing various fields, including robotics, natural language processing, and brain-computer interfaces, by creating AI systems that are more energy-efficient, learn more effectively, and generalize better to new situations.
Papers
Core-Periphery Principle Guided Redesign of Self-Attention in Transformers
Xiaowei Yu, Lu Zhang, Haixing Dai, Yanjun Lyu, Lin Zhao, Zihao Wu, David Liu, Tianming Liu, Dajiang Zhu
CP-CNN: Core-Periphery Principle Guided Convolutional Neural Network
Lin Zhao, Haixing Dai, Zihao Wu, Dajiang Zhu, Tianming Liu