返回
Learning from Few Samples with Memory Network
DOI:10.1007/s12559-017-9507-z.png)
摘要
En 中文
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.
Keyword:
Memory
Multi-layer perceptron
Neural network
Recognition
Prior knowledge
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.3
论文数:
1.6K
被引数:
3.6K
机构
引用论文
The effect of a novel extracorporeal cytokine hemoadsorption device on IL-6 elimination in septic patients: A randomized controlled trial
PLOS ONE
IF0
Electrolyte–electrolyte phase separation under the influence of a DC magnetic field在直流磁场影响下的电解质-电解质相分离
Movement of electrolyte at metal etching and deposition under a non-uniform steady magnetic field在非均匀稳态磁场下金属蚀刻和沉积过程中电解质的运动
Iminophosphorane-Mediated Synthesis of the Carbon Skeleton of the Azafluoranthene Alkaloids Rufescine and Imeluteine
Synlett
IF0

