Title |
A Factor Graph Description of Deep Temporal Active Inference
|
---|---|
Published in |
Frontiers in Computational Neuroscience, October 2017
|
DOI | 10.3389/fncom.2017.00095 |
Pubmed ID | |
Authors |
Bert de Vries, Karl J. Friston |
Abstract |
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. |
X Demographics
As of 1 July 2024, you may notice a temporary increase in the numbers of X profiles with Unknown location. Click here to learn more.
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 1 | 8% |
Netherlands | 1 | 8% |
Unknown | 11 | 85% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 13 | 100% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 55 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 13 | 24% |
Researcher | 12 | 22% |
Professor > Associate Professor | 6 | 11% |
Student > Bachelor | 4 | 7% |
Professor | 3 | 5% |
Other | 10 | 18% |
Unknown | 7 | 13% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 9 | 16% |
Neuroscience | 7 | 13% |
Computer Science | 7 | 13% |
Psychology | 5 | 9% |
Agricultural and Biological Sciences | 4 | 7% |
Other | 13 | 24% |
Unknown | 10 | 18% |