A Hierarchical Predictive Coding Model of Object Recognition in Natural Images
- Submitting institution
-
King's College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 111208743
- Type
- D - Journal article
- DOI
-
10.1007/s12559-016-9445-1
- Title of journal
- Cognitive Computation
- Article number
- -
- First page
- 151
- Volume
- 9
- Issue
- 2
- ISSN
- 1866-9956
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
0
- Research group(s)
-
-
- Citation count
- 29
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents the first demonstration that predictive coding, an influential theory in the neurosciences (Rao and Ballard, Nature Neuroscience, 1999), can be applied to practical object recognition tasks. This is rigorously demonstrated using a series of experiments that follow standard procedures, and that show competitive performance compared to many alternative algorithms. This provides important support for the predictive coding theory of brain function. In addition, this work has partially inspired more recent demonstrations (Wen et. al. ICML 2018; Han et. al. NeurIPS 2018) showing that deep neural networks based on predictive coding have advantages over standard convolutional neural networks.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -