Inference as Control predicts Phase transitions in when Feedback is useful

Simple item page
dc.contributor.advisorPitkow, Xaqen_US
dc.creatorBoominathan, Lokeshen_US
dc.date.accessioned2021-08-16T19:53:44Zen_US
dc.date.available2021-08-16T19:53:44Zen_US
dc.date.created2021-08en_US
dc.date.issued2021-08-09en_US
dc.date.submittedAugust 2021en_US
dc.date.updated2021-08-16T19:53:44Zen_US
dc.description.abstractSensory observations about the world are invariably ambiguous. Inference about the world's latent variables is thus an important computation for the brain. However, computational constraints limit the performance of these computations. These constraints include energetic costs for neural activity and noise for every channel. Efficient coding is a prominent theory that describes how limited resources can be used best. In one incarnation, this leads to a theory of predictive coding, where predictions are subtracted from signals, reducing the cost of sending something that is already known. This theory does not, however, account for the costs or noise associated with those predictions. Here we offer a theory that accounts for both feedforward and feedback costs, and noise in all computations. We formulate this inference problem as message-passing on a graph whereby feedback is viewed as a control signal aiming to maximize how well an inference tracks a target state while minimizing the costs of computation. We apply this novel formulation of inference as control to the canonical problem of inferring the hidden scalar state of a linear dynamical system with Gaussian variability. Our theory predicts the gain of optimal predictive feedback and how it is incorporated into the inference computation. We show that there is a non-monotonic dependence of optimal feedback gain as a function of both the computational parameters and the world dynamics, and we reveal phase transitions in whether feedback provides any utility in optimal inference under computational costs.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationBoominathan, Lokesh. "Inference as Control predicts Phase transitions in when Feedback is useful." (2021) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/111222">https://hdl.handle.net/1911/111222</a>.en_US
dc.identifier.urihttps://hdl.handle.net/1911/111222en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectBayesian Inferenceen_US
dc.subjectControl Theoryen_US
dc.subjectPredictive Codingen_US
dc.subjectEfficient Codingen_US
dc.titleInference as Control predicts Phase transitions in when Feedback is usefulen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentElectrical and Computer Engineeringen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Scienceen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
BOOMINATHAN-DOCUMENT-2021.pdf
Size:
2.06 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.85 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.61 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations