Related Experiment Video
Updated: Oct 27, 2025
13:04
Measuring the Subjective Value of Risky and Ambiguous Options using Experimental Economics and Functional MRI Methods
Published on: September 19, 2012
12.2K
Realizing Active Inference in Variational Message Passing: The Outcome-Blind Certainty Seeker.
Théophile Champion1, Marek Grześ2, Howard Bowman3
1University of Kent, School of Computing, Canterbury CT2 7NZ, U.K. tmac3@kent.ac.uk.
Neural Computation
|July 19, 2021
Summary
Active inference, a unified theory for brain function and AI planning, is made more accessible through a simplified mathematical treatment. This enables researchers to develop advanced generative models for active inference and AI applications.
Area of Science:
- Neuroscience
- Artificial Intelligence (AI)
Background:
- Active inference offers a unified framework for understanding brain function and AI planning.
- Complex mathematics currently hinders the development of new active inference models.
Purpose of the Study:
- To provide a complete mathematical treatment of active inference in discrete time and state spaces.
- To derive update equations for creating novel active inference models.
Main Methods:
- Leveraging the connection between active inference and variational message passing.
- Applying a fully factorized variational distribution to simplify expected free energy.
Main Results:
- A clear mathematical framework for active inference in discrete settings.
- Derivation of update equations applicable to any new model.
- Demonstration that simplified expected free energy provides priors over policies.
Conclusions:
- This work simplifies active inference, facilitating its application in neuroscience and AI.
- The derived equations enable the creation of advanced generative models for active inference.
- Future extensions can support advanced policy optimization through structure learning and belief propagation.
More Related Videos
Related Concept Videos
00:59Propagation of Uncertainty from Random Error
1.3K
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
1.3K
01:31Confirmation Biases
7.4K
The confirmation bias is the tendency to focus on information that confirms our existing beliefs and ignore information that is inconsistent with our expectations. For example, if you think that your professor is not very nice, you notice all of the instances of rude behavior exhibited by the professor while ignoring the countless pleasant interactions he is involved in on a daily basis. Have you ever fallen prey to the confirmation bias, either as the source or target of such bias?
7.4K
01:10Propagation of Uncertainty from Systematic Error
1.1K
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
1.1K
01:12Hindsight Biases
4.1K
Hindsight bias leads you to believe that the event you just experienced was predictable, even though it really wasn’t. In other words, you knew all along that things would turn out the way they did. Can you relate this to the phrase "Hindsight is 20/20" now?
4.1K
01:15Theory of Attribution I: Correspondent Inference Theory
86
Correspondent inference theory, proposed by Jones and Davis in 1965, seeks to explain how individuals infer stable personality traits from observed behaviors. It suggests that people attribute actions to underlying dispositions rather than external circumstances, particularly when the behavior appears intentional and socially significant.Voluntary Behavior and Dispositional AttributionAccording to this theory, individuals are more likely to attribute behavior to personal traits when it appears...
86
00:59Uncertainty: Overview
1.2K
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
1.2K