A Hierarchical Predictive Coding Model of Object Recognition in Natural Images

Predictive coding has been proposed as a model of the hierarchical perceptual inference process performed in the cortex. However, results demonstrating that predictive coding is capable of performing the complex inference required to recognise objects in natural images have not previously been prese...

Full description

Saved in:
Bibliographic Details
Published in:Cognitive computation Vol. 9; no. 2; pp. 151 - 167
Main Author: Spratling, M. W.
Format: Journal Article
Language:English
Published: New York Springer US 01.04.2017
Springer Nature B.V
Subjects:
Algorithms
Artificial Intelligence
Biomedical and Life Sciences
Biomedicine
Computation by Abstract Devices
Computational Biology/Bioinformatics
Dictionaries
Image coding
Inference
Inverse problems
Neural networks
Neurons
Neurosciences
Object recognition
Occlusion
Performance prediction
Predictive coding
Deep neural networks
Object recognition
Sparse coding
Neural networks
Implicit shape model
ISSN:1866-9956, 1866-9964
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Predictive coding has been proposed as a model of the hierarchical perceptual inference process performed in the cortex. However, results demonstrating that predictive coding is capable of performing the complex inference required to recognise objects in natural images have not previously been presented. This article proposes a hierarchical neural network based on predictive coding for performing visual object recognition. This network is applied to the tasks of categorising hand-written digits, identifying faces, and locating cars in images of street scenes. It is shown that image recognition can be performed with tolerance to position, illumination, size, partial occlusion, and within-category variation. The current results, therefore, provide the first practical demonstration that predictive coding (at least the particular implementation of predictive coding used here; the PC/BC-DIM algorithm) is capable of performing accurate visual object recognition.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1866-9956
1866-9964
DOI:10.1007/s12559-016-9445-1