Learning from Few Samples with Memory Network

Neural networks (NN) have achieved great successes in pattern recognition and machine learning. However, the success of a NN usually relies on the provision of a sufficiently large number of data samples as training data. When fed with a limited data set, a NN’s performance may be degraded significa...

Full description

Saved in:
Bibliographic Details
Published in:Cognitive computation 2018-02, Vol.10 (1), p.15-22
Main Authors: Zhang, Shufei, Huang, Kaizhu, Zhang, Rui, Hussain, Amir
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Artificial neural networks
Biomedical and Life Sciences
Biomedicine
Computation by Abstract Devices
Computational Biology/Bioinformatics
Datasets
Deep learning
Knowledge
Language
Machine learning
Memory
Multilayer perceptrons
Multilayers
Neural networks
Neurosciences
Optimization
Pattern recognition
Performance degradation
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:Neural networks (NN) have achieved great successes in pattern recognition and machine learning. However, the success of a NN usually relies on the provision of a sufficiently large number of data samples as training data. When fed with a limited data set, a NN’s performance may be degraded significantly. In this paper, a novel NN structure is proposed called a memory network. It is inspired by the cognitive mechanism of human beings, which can learn effectively, even from limited data. Taking advantage of the memory from previous samples, the new model achieves a remarkable improvement in performance when trained using limited data. The memory network is demonstrated here using the multi-layer perceptron (MLP) as a base model. However, it would be straightforward to extend the idea to other neural networks, e.g., convolutional neural networks (CNN). In this paper, the memory network structure is detailed, the training algorithm is presented, and a series of experiments are conducted to validate the proposed framework. Experimental results show that the proposed model outperforms traditional MLP-based models as well as other competitive algorithms in response to two real benchmark data sets.
ISSN:1866-9956
1866-9964
DOI:10.1007/s12559-017-9507-z