A Caltech Library Service

Learned Feedback & Feedforward Perception & Control


Marino, Joseph Louis (2021) Learned Feedback & Feedforward Perception & Control. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/4mjd-ce53.


The notions of feedback and feedforward information processing gained prominence under cybernetics, an early movement at the dawn of computer science and theoretical neuroscience. Negative feedback processing corrects errors, whereas feedforward processing makes predictions, thereby preemptively reducing errors. A key insight of cybernetics was that such processes can be applied to both perception, or state estimation, and control, or action selection. The remnants of this insight are found in many modern areas, including predictive coding in neuroscience and deep latent variable models in machine learning. This thesis draws on feedback and feedforward ideas developed within predictive coding, adapting them to improve machine learning techniques for perception (Part II) and control (Part III). Upon establishing these conceptual connections, in Part IV, we traverse this bridge, from machine learning back to neuroscience, arriving at new perspectives on the correspondences between these fields.

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:Neuroscience, Machine Learning
Degree Grantor:California Institute of Technology
Division:Biology and Biological Engineering
Major Option:Computation and Neural Systems
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Yue, Yisong (co-advisor)
  • Perona, Pietro (co-advisor)
Thesis Committee:
  • Yue, Yisong
  • Perona, Pietro
  • O'Doherty, John P.
  • Tsao, Doris Y. (chair)
  • Rao, Rajesh P. N.
Defense Date:21 May 2021
Record Number:CaltechTHESIS:05272021-042158260
Persistent URL:
Related URLs:
URLURL TypeDescription adapted for chapter 3 adapted for chapter 4 adapted for chapter 8 adapted for chapter 5 adapted for chapter 6 adapted for chapter 7 adapted for chapter 6 adapted for chapter 9 DocumentArticle extends chapter 5 version of chapter 8
Marino, Joseph Louis0000-0001-6387-8062
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:14178
Deposited By: Joseph Marino
Deposited On:07 Jun 2021 15:47
Last Modified:08 Nov 2023 00:44

Thesis Files

[img] PDF - Final Version
See Usage Policy.


Repository Staff Only: item control page