Hong Sungcheol
Department of Electronic & Electrical Convergence Engineering, Hongik University, Sejong 30016, Republic of Korea.
Micromachines (Basel). 2025 May 3;16(5):557. doi: 10.3390/mi16050557.
Brain-inspired models in artificial intelligence (AI) originated from foundational insights in neuroscience. In recent years, this relationship has been moving toward a mutually reinforcing feedback loop. Currently, AI is significantly contributing to advancing our understanding of neuroscience. In particular, when combined with wireless optogenetics, AI enables experiments without physical constraints. Furthermore, AI-driven real-time analysis facilitates closed-loop control, allowing experimental setups across a diverse range of scenarios. And a deeper understanding of these neural networks may, in turn, contribute to future advances in AI. This work demonstrates the synergy between AI and miniaturized neural technology, particularly through wireless optogenetic systems designed for closed-loop neural control. We highlight how AI is now revolutionizing neuroscience experiments from decoding complex neural signals and quantifying behavior, to enabling closed-loop interventions and high-throughput phenotyping in freely moving subjects. Notably, AI-integrated wireless implants can monitor and modulate biological processes with unprecedented precision. We then recount how neuroscience insights derived from AI-integrated neuroscience experiments can potentially inspire the next generation of machine intelligence. Insights gained from these technologies loop back to inspire more efficient and robust AI systems. We discuss future directions in this positive feedback loop between AI and neuroscience, arguing that the coevolution of the two fields, grounded in technologies like wireless optogenetics and guided by reciprocal insight, will accelerate progress in both, while raising new challenges and opportunities for interdisciplinary collaboration.
人工智能（AI）中受大脑启发的模型源自神经科学的基础见解。近年来，这种关系正朝着相互强化的反馈循环发展。目前，人工智能在推动我们对神经科学的理解方面发挥着重要作用。特别是，当与无线光遗传学相结合时，人工智能能够实现不受物理限制的实验。此外，人工智能驱动的实时分析有助于闭环控制，允许在各种场景下进行实验设置。而对这些神经网络的更深入理解反过来可能有助于人工智能未来的发展。这项工作展示了人工智能与小型化神经技术之间的协同作用，特别是通过为闭环神经控制设计的无线光遗传系统。我们强调了人工智能如今如何正在彻底改变神经科学实验，从解码复杂的神经信号和量化行为，到在自由活动的受试者中实现闭环干预和高通量表型分析。值得注意的是，集成人工智能的无线植入物能够以前所未有的精度监测和调节生物过程。然后我们讲述了从集成人工智能的神经科学实验中获得的神经科学见解如何有可能启发下一代机器智能。从这些技术中获得的见解又会回馈回来，以启发更高效、更强大的人工智能系统。我们讨论了人工智能与神经科学之间这种正反馈循环的未来方向，认为这两个领域的共同进化，以无线光遗传学等技术为基础，并受到相互启发的引导，将加速两者的进展，同时为跨学科合作带来新的挑战和机遇。
