Fast Inference Predictive Coding: A Novel Model for Constructing Deep Neural Networks

As a biomimetic model of visual information processing, predictive coding (PC) has become increasingly popular for explaining a range of neural responses and many aspects of brain organization. While the development of PC model is encouraging in the neurobiology community, its practical applications...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2019-04, Vol.30 (4), p.1150-1165
Main Authors: Song, Zengjie, Zhang, Jiangshe, Shi, Guang, Liu, Junmin
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Biomimetics
Brain
Brain architecture
Brain modeling
Classification
Coding
Data processing
Deep learning (DL)
Feature extraction
Image classification
Image processing
Inference
inference mechanisms
Information processing
Learning algorithms
Machine learning
Mathematical model
Nervous system
Neural coding
Neural networks
Neurons
Neurosciences
predictive coding (PC)
Predictive models
Regression models
Representations
Task analysis
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a biomimetic model of visual information processing, predictive coding (PC) has become increasingly popular for explaining a range of neural responses and many aspects of brain organization. While the development of PC model is encouraging in the neurobiology community, its practical applications in machine learning (e.g., image classification) have not been fully explored yet. In this paper, a novel image processing model called fast inference PC (FIPC) is presented for image representation and classification. Compared with the basic PC model, a regression procedure and a classification layer have been added to the proposed FIPC model. The regression procedure is used to learn regression mappings that achieve fast inference at test time, while the classification layer can instruct the model to extract more discriminative features. In addition, effective learning and fine-tuning algorithms are developed for the proposed model. Experimental results obtained on four image benchmark data sets show that our model is able to directly and fast infer representations and, simultaneously, produce lower error rates on image classification tasks.
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2018.2862866