TY - JOUR
T1 - A GPU-based computational framework that bridges neuron simulation and artificial intelligence
AU - Zhang, Yichen
AU - He, Gan
AU - Ma, Lei
AU - Liu, Xiaofei
AU - Hjorth, J. J.Johannes
AU - Kozlov, Alexander
AU - He, Yutao
AU - Zhang, Shenjian
AU - Kotaleski, Jeanette Hellgren
AU - Tian, Yonghong
AU - Grillner, Sten
AU - Du, Kai
AU - Huang, Tiejun
N1 - Publisher Copyright:
© 2023, Springer Nature Limited.
PY - 2023/12
Y1 - 2023/12
N2 - Biophysically detailed multi-compartment models are powerful tools to explore computational principles of the brain and also serve as a theoretical framework to generate algorithms for artificial intelligence (AI) systems. However, the expensive computational cost severely limits the applications in both the neuroscience and AI fields. The major bottleneck during simulating detailed compartment models is the ability of a simulator to solve large systems of linear equations. Here, we present a novel Dendritic Hierarchical Scheduling (DHS) method to markedly accelerate such a process. We theoretically prove that the DHS implementation is computationally optimal and accurate. This GPU-based method performs with 2-3 orders of magnitude higher speed than that of the classic serial Hines method in the conventional CPU platform. We build a DeepDendrite framework, which integrates the DHS method and the GPU computing engine of the NEURON simulator and demonstrate applications of DeepDendrite in neuroscience tasks. We investigate how spatial patterns of spine inputs affect neuronal excitability in a detailed human pyramidal neuron model with 25,000 spines. Furthermore, we provide a brief discussion on the potential of DeepDendrite for AI, specifically highlighting its ability to enable the efficient training of biophysically detailed models in typical image classification tasks.
AB - Biophysically detailed multi-compartment models are powerful tools to explore computational principles of the brain and also serve as a theoretical framework to generate algorithms for artificial intelligence (AI) systems. However, the expensive computational cost severely limits the applications in both the neuroscience and AI fields. The major bottleneck during simulating detailed compartment models is the ability of a simulator to solve large systems of linear equations. Here, we present a novel Dendritic Hierarchical Scheduling (DHS) method to markedly accelerate such a process. We theoretically prove that the DHS implementation is computationally optimal and accurate. This GPU-based method performs with 2-3 orders of magnitude higher speed than that of the classic serial Hines method in the conventional CPU platform. We build a DeepDendrite framework, which integrates the DHS method and the GPU computing engine of the NEURON simulator and demonstrate applications of DeepDendrite in neuroscience tasks. We investigate how spatial patterns of spine inputs affect neuronal excitability in a detailed human pyramidal neuron model with 25,000 spines. Furthermore, we provide a brief discussion on the potential of DeepDendrite for AI, specifically highlighting its ability to enable the efficient training of biophysically detailed models in typical image classification tasks.
UR - http://www.scopus.com/inward/record.url?scp=85171630487&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85171630487&partnerID=8YFLogxK
U2 - 10.1038/s41467-023-41553-7
DO - 10.1038/s41467-023-41553-7
M3 - Article
C2 - 37723170
AN - SCOPUS:85171630487
SN - 2041-1723
VL - 14
JO - Nature communications
JF - Nature communications
IS - 1
M1 - 5798
ER -