Canonical neural networks perform active inference.

Canonical neural networks perform active inference.
复制标题

DOI:
10.1038/s42003-021-02994-2
复制
发表时间:
2022-01-14
影响因子:
5.9
通讯作者:
Friston KJ
Friston KJ
中科院分区:
生物学2区
文献类型:
--
作者:
Isomura T;Shimazaki H;Friston KJ

文献摘要

参考文献

被引文献

相似文献

这项工作考虑了一类包含速率编码模型的规范神经网络,其中神经活动和可塑性最小化了共同的成本函数-可塑性是用一定的延迟调制的。我们表明,这种神经网络隐式地执行主动推理和学习,以最小化与未来结果相关的风险。数学分析表明,这种生物优化可以在众所周知的部分观察马尔可夫决策过程模型的形式下,作为模型证据的最大化,或等效的变分自由能的最小化。这一等价性表明,Hebbian可塑性的延迟调制——伴随着放电阈值的适应——是实现贝叶斯最优推理和控制的充分的神经元基质。我们用迷宫任务的数值分析证实了这一命题。该理论在贝叶斯信念更新方面提供了典型神经网络的普遍特征,并提供了对计划和自适应行为控制的神经机制的见解。Takuya Isomura, Hideaki Shimazaki和Karl Friston进行了数学分析,表明神经网络隐式地进行主动推理和学习,以最小化与未来结果相关的风险。他们的工作提供了对计划和适应性行为控制的神经机制的深入了解。
This work considers a class of canonical neural networks comprising rate coding models, wherein neural activity and plasticity minimise a common cost function—and plasticity is modulated with a certain delay. We show that such neural networks implicitly perform active inference and learning to minimise the risk associated with future outcomes. Mathematical analyses demonstrate that this biological optimisation can be cast as maximisation of model evidence, or equivalently minimisation of variational free energy, under the well-known form of a partially observed Markov decision process model. This equivalence indicates that the delayed modulation of Hebbian plasticity—accompanied with adaptation of firing thresholds—is a sufficient neuronal substrate to attain Bayes optimal inference and control. We corroborated this proposition using numerical analyses of maze tasks. This theory offers a universal characterisation of canonical neural networks in terms of Bayesian belief updating and provides insight into the neuronal mechanisms underlying planning and adaptive behavioural control. Takuya Isomura, Hideaki Shimazaki and Karl Friston perform mathematical analysis to show that neural networks implicitly perform active inference and learning to minimise the risk associated with future outcomes. Their work provides insight into the neuronal mechanisms underlying planning and adaptive behavioural control.
DOI: 10.3389/fncir.2015.00085
发表时间: 2015
影响因子: 3.5
作者:
Frémaux N;Gerstner W
通讯作者: Gerstner W
DOI: 10.1162/neco_a_00912
发表时间: 2017-01-01
期刊: NEURAL COMPUTATION
影响因子: 2.9
作者:
Friston, Karl;FitzGerald, Thomas;Pezzulo, Giovanni
通讯作者: Pezzulo, Giovanni
DOI: 10.1038/nn.2398
发表时间: 2009-10
影响因子: 25
作者:
Benucci, Andrea;Ringach, Dario L.;Carandini, Matteo
通讯作者: Carandini, Matteo
DOI: 10.1113/jphysiol.1973.sp010273
发表时间: 1973-01-01
影响因子: 5.5
作者:
BLISS, TVP;LOMO, T
通讯作者: LOMO, T
DOI: 10.1162/neco.1995.7.5.889
发表时间: 1995-09-01
期刊: NEURAL COMPUTATION
影响因子: 2.9
作者:
DAYAN, P;HINTON, GE;ZEMEL, RS
通讯作者: ZEMEL, RS