|Appears in Collections:||Computing Science and Mathematics Journal Articles|
|Peer Review Status:||Refereed|
|Title:||Learning from Few Samples with Memory Network|
|Citation:||Zhang S, Huang K, Zhang R & Hussain A (2018) Learning from Few Samples with Memory Network. Cognitive Computation, 10 (1), pp. 15-22. https://doi.org/10.1007/s12559-017-9507-z|
|Abstract:||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.|
|Rights:||This item has been embargoed for a period. During the embargo please use the Request a Copy feature at the foot of the Repository record to request a copy directly from the author. You can only request a copy if you wish to use this work for your own research or private study. Publisher policy allows this work to be made available in this repository; The final publication is available at Springer via https://doi.org/10.1007/s12559-017-9507-z|
|memory_network_ML3-2.pdf||Fulltext - Accepted Version||1.34 MB||Adobe PDF||View/Open|
This item is protected by original copyright
Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/
If you believe that any material held in STORRE infringes copyright, please contact firstname.lastname@example.org providing details and we will remove the Work from public display in STORRE and investigate your claim.