Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Toward predictive machine learning for active vision
Nov 07, 2017 (modified: Nov 07, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:We develop a comprehensive description of the active inference framework, as proposed by Friston (2010), under a machine-learning compliant perspective. Stemming from a biological inspiration and the auto-encoding principles, a sketch of a cognitive architecture is proposed that should provide ways to implement estimation-oriented control policies under a POMDP perspective.
Computer simulations illustrate the effectiveness of the approach through a foveated inspection the input data.
The pros and cons of the control policy are reviewed in details, showing interesting promises in term of processing compression, but also putative risks of a confirmation bias that may degrade te recognition performance if the model is too optimistic about is own predictions. The presented formalism is fully compliant with the auto-encoding framework and would deserve further developments under variational encoding architectures.
TL;DR:Pros and cons of saccade-based computer vision under a predictive coding perspective
Keywords:active inference, predictive coding, motor control
Enter your feedback below and we'll get back to you as soon as possible.