A Factor Graph Description of Deep Temporal Active Inference.

A Factor Graph Description of Deep Temporal Active Inference.
复制标题

DOI:
10.3389/fncom.2017.00095
复制
发表时间:
2017
影响因子:
3.2
通讯作者:
Friston KJ
Friston KJ
中科院分区:
医学4区
文献类型:
--
作者:
de Vries B;Friston KJ

文献摘要

参考文献

被引文献

相似文献

主动推理是自由能原理的推论,该原理规定了自组织生物制剂如何与环境相互作用。主动推理过程的研究依赖于生成概率模型的定义,以及在该模型下自由能泛函如何通过神经元消息传递而最小化的描述。本文介绍了用Forney式因子图(FFG)来描述主动推理过程的教程。FFG框架既提供了概率模型的有洞察力的表示,也提供了从生物学上看似合理的推理方案,原则上可以在计算机模拟中自动执行。作为一个说明性的例子,我们给出了一个用于深度时态主动推理过程的FFG。该图清楚地显示了在适当的生成性策略模型中,通过预期自由能最小化进行的策略选择是如何从自由能最小化本身产生的。
Active inference is a corollary of the Free Energy Principle that prescribes how self-organizing biological agents interact with their environment. The study of active inference processes relies on the definition of a generative probabilistic model and a description of how a free energy functional is minimized by neuronal message passing under that model. This paper presents a tutorial introduction to specifying active inference processes by Forney-style factor graphs (FFG). The FFG framework provides both an insightful representation of the probabilistic model and a biologically plausible inference scheme that, in principle, can be automatically executed in a computer simulation. As an illustrative example, we present an FFG for a deep temporal active inference process. The graph clearly shows how policy selection by expected free energy minimization results from free energy minimization per se, in an appropriate generative policy model.
DOI: 10.1016/j.neuron.2012.10.038
发表时间: 2012-11-21
期刊: Neuron
影响因子: 16.2
作者:
Bastos AM;Usrey WM;Adams RA;Mangun GR;Fries P;Friston KJ
通讯作者: Friston KJ
DOI: 10.3389/fnsys.2016.00049
发表时间: 2016-06-07
影响因子: 3
作者:
Campbell, John O.
通讯作者: Campbell, John O.
DOI: 10.1109/msp.2004.1267047
发表时间: 2004-01-01
影响因子: 14.9
作者:
Loeliger, HA
通讯作者: Loeliger, HA
DOI: 10.1109/tit.2017.2716422
发表时间: 2017-09-01
影响因子: 2.5
作者:
Loeliger, Hans-Andrea;Vontobel, Pascal O.
通讯作者: Vontobel, Pascal O.
DOI: 10.1098/rstb.2014.0169
发表时间: 2015-05-19
期刊: Philosophical transactions of the Royal Society of London. Series B, Biological sciences
影响因子: --
作者:
Kanai R;Komura Y;Shipp S;Friston K
通讯作者: Friston K