Preface: Brain-Inspired AI Research

Large AGI (artificial general intelligence) models, represented by OpenAI's GPT-4, DALL-E, Sora, etc., have amazed the world by exhibiting superior capabilities on a variety of NLP and text-to-image/video generation tasks.The success of these models was achieved by exploiting ultra-scale training data, ultra-scale computational models, and unlimited computing power.This brute force approach, however, is not only making an adverse impact on global warming prevention, but also raising skepticism on whether such a development path can really achieve true AGI systems.Recently, there have been increasing scientific studies that report the delusion phenomenon of the AGI models, mainly caused by their inability to learn correct knowledge and correct world models.On the other hand, human brain consumes less than 30 W of energy, and has superior learning, cognitive, reasoning, and creative abilities compared with most existing AI systems.Therefore, it is a very promising research direction to study the working mechanism of human brain, and develop human brain-inspired AGI models.In fact, many famous and widely applied AI models/methods, such as convolution neural networks (CNN), spiking neural networks (SNN), long short-term memory (LSTM), and reinforcement learning, are all developed from inspirations of research discoveries of human brain.This special topic focuses on recent developments in cognitive science and AI research.It consists of five invited manuscripts written by distinguished scholars in the fields of cognitive science and artificial intelligence.A survey manuscript summarizes mainstream AI research into three branches according to the three-layer framework proposed by David Marr and reviews the roles of cognitive science in inspiring the three-layer AI research.Additionally, it proposes eight important research directions and their major scientific issues in the field of brain-inspired AI research.Two manuscripts in this special issue reveal the similarities and differences in feedback processing, and in naturalistic texture processing between primate brain and AI systems.We have also included two manuscripts that describe the latest cognitive scientific discoveries in human visual system, which inspire the developments of the human-level vision system, and the dual-pathway neural network architecture.I really appreciate all the authors for contributing their efforts and valuable time to this special topic, and I expect that the readers of this special topic will get inspired and excited about participating in future brain-inspired AI research.