智能神经假体——神经信息传递的非线性建模
钱存乐;林芃;潘纲;
摘要(Abstract)：
智能神经假体是一种替代大脑特定功能的电子装置，为受损的大脑区域开辟一条人工电子通路，通过重塑神经信息传递，修复因神经受损导致的大脑智能缺失。当前，对于这种“替代通路”的设计更多来源于局部功能连接模型，而缺乏针对不同脑区间高度非线性连接的精细建模，这限制了神经假体可重建的感认知能力。本文旨在探讨面向智能神经假体神经信息传递的非线性建模问题，为实现更精准的智能神经假体提供拟合度更高、性能更稳定的理论模型。本文首先简要回顾神经假体的研究进展;其次，针对现有神经信息传递模型非线性表达能力差、性能不稳定等不足进行分析;最后，探讨非线性神经信息传递模型的设计与实践。
关键词(KeyWords)： 智能神经假体;神经信息传递模型;非线性建模;混合智能
基金项目(Foundation): 国家自然科学基金（61925603、U1909202）;; 浙江省重点研发项目(2020C03004)
作者(Authors): 钱存乐;林芃;潘纲;
参考文献(References)：
- [1]RIEKE F,WARLAND D,STEVENINCK R D R V,et al.Spikes:exploring the neural code[M].MIT Press,1999.
- [2]BA T,WANG B,LIU H,et al.Prevalence and causes of vision loss in China from 1990 to 2019:fndings from the Global Burden of Disease Study 2019[J].The Lancet Public Health,2020,5(12):E682-E691.
- [3]REN R,QI J,LIN S,et al.The China Alzheimer report 2022[J].General Psychiatry,2022,35(1):e100751.
- [4]NICOLELIS M A.Chronic,multisite,multielectrode recordings in macaque monkeys[C]//Proceedings of the National Academy of Sciences,2003,100(19):11041-11046.
- [5]ROLF E.智能神经假体:心理与技术问题[J].生命科学,2009(2).
- [6]BERGER T W,HAMPSON R E,SONG D,et al.A cortical neural prosthesis for restoring and enhancing memory[J].Journal of Neural Engineering,2011,8(4):046017.
- [7]WU Z,ZHOU Y,SHI Z,et al.Cyborg intelligence:recent progress and future directions[J].IEEE Intelligent Systems,2016,31(6):44-50.
- [8]吴朝晖,潘纲.脑科学的新手段新技术：信息+系统+智能视角[J].科学通报,2015(10):912-916.
- [9]XING D,QIAN C,LI H,et al.Predicting spike trains from PMd to M1 using discrete time rescaling targeted GLM[J].IEEETransactions on Cognitive and Developmental Systems,2018,10(2):194-204.
- [10]ECKMILLER R,NEUMANN D,BARUTH O.Tunable retina encoders for retina implants:why and how[J].Journal of Neural Engineering,2005,2(1):S91.
- [11]HOCHBERG L R,BACHER D,JAROSIEWICZ B,et al.Reach and grasp by people with tetraplegia using a neurally controlled robotic arm[J].Nature,2012,485(7398):372-375.
- [12]WANG F,WANG Y,XU K,et al.Quantized attention-gated kernel reinforcement learning for brain-machine interface decoding[J].IEEE Transactions on Neural Networks&Learning Systems,2015,28(4):873.
- [13]SONG D,CHAN R H M,MARMARELIS V Z,et al.Nonlinear dynamic modeling of spike train transformations for hippocampal-cortical prostheses[J].IEEE Transactions on Biomedical Engineering,2007,54(6):1053-1066.
- [14]TRUCCOLO W,EDEN U T,FELLOWS M R,et al.A point process framework for relating neural spiking activity to spiking history,neural ensemble,and extrinsic covariate effects[J].Journal of Neurophysiology,2005,93(2):1074-1089.
- [15]QIAN C,SUN X,ZHANG S,et al.Nonlinear modeling of neural interaction for spike prediction using the staged pointprocess model[J].Neural Computation,2018:1-38.
- [16]SCHWARTZ O,PILLOW J W,RUST N C,et al.Spike-triggered neural characterization[J].Journal of Vision,2006,6(4):484.
- [17]GERSTNER W,KISTLER W.Spiking neuron models:single neurons,populations,plasticity[M].Cambridge University Press,2002.
- [18]GENG K,MARMARELIS V Z.Methodology of recurrent laguerre-volterra network for modeling nonlinear dynamic systems[J].IEEE Transactions on Neural Networks and Learning Systems,2016:1-13.
- [19]Qian C,Sun X,Zheng X,et al.Binless kernel machine:modeling spike train transformation for cognitive neural prostheses[J].Neural Computation,2020,32(10):1863-1900.
- [20]STEPHEN B L V,STEPHEN B L V.Convex optimization[M].Cambridge University Press,2006.
- [21]HASLINGER R,PIPA G,BROWN E N.Discrete time rescaling theorem:determining goodness of fit for discrete time statistical models of neural spiking[J].Neural Computation,2010,22(10):2477-2506.