TY - JOUR
T1 - Network model with internal complexity bridges artificial intelligence and neuroscience
AU - He, Linxuan
AU - Xu, Yunhui
AU - He, Weihua
AU - Lin, Yihan
AU - Tian, Yang
AU - Wu, Yujie
AU - Wang, Wenhui
AU - Zhang, Ziyang
AU - Han, Junwei
AU - Tian, Yonghong
AU - Xu, Bo
AU - Li, Guoqi
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer Nature America, Inc. 2024.
PY - 2024/8
Y1 - 2024/8
N2 - Artificial intelligence (AI) researchers currently believe that the main approach to building more general model problems is the big AI model, where existing neural networks are becoming deeper, larger and wider. We term this the big model with external complexity approach. In this work we argue that there is another approach called small model with internal complexity, which can be used to find a suitable path of incorporating rich properties into neurons to construct larger and more efficient AI models. We uncover that one has to increase the scale of the network externally to stimulate the same dynamical properties. To illustrate this, we build a Hodgkin–Huxley (HH) network with rich internal complexity, where each neuron is an HH model, and prove that the dynamical properties and performance of the HH network can be equivalent to a bigger leaky integrate-and-fire (LIF) network, where each neuron is a LIF neuron with simple internal complexity.
AB - Artificial intelligence (AI) researchers currently believe that the main approach to building more general model problems is the big AI model, where existing neural networks are becoming deeper, larger and wider. We term this the big model with external complexity approach. In this work we argue that there is another approach called small model with internal complexity, which can be used to find a suitable path of incorporating rich properties into neurons to construct larger and more efficient AI models. We uncover that one has to increase the scale of the network externally to stimulate the same dynamical properties. To illustrate this, we build a Hodgkin–Huxley (HH) network with rich internal complexity, where each neuron is an HH model, and prove that the dynamical properties and performance of the HH network can be equivalent to a bigger leaky integrate-and-fire (LIF) network, where each neuron is a LIF neuron with simple internal complexity.
UR - http://www.scopus.com/inward/record.url?scp=85201391423&partnerID=8YFLogxK
U2 - 10.1038/s43588-024-00674-9
DO - 10.1038/s43588-024-00674-9
M3 - 文章
AN - SCOPUS:85201391423
SN - 2662-8457
VL - 4
SP - 584
EP - 599
JO - Nature Computational Science
JF - Nature Computational Science
IS - 8
ER -