DocumentCode :
3226620
Title :
HNNP - A Hybrid Neural Network Plait for Improving Image Classification with Additional Side Information
Author :
Janning, Ruth ; Schatten, Carlotta ; Schmidt-Thieme, Lars
Author_Institution :
Inf. Syst. & Machine Learning Lab. (ISMLL), Univ. of Hildesheim, Hildesheim, Germany
fYear :
2013
fDate :
4-6 Nov. 2013
Firstpage :
24
Lastpage :
29
Abstract :
Most of the artificial intelligence and machine learning researches deal with big data today. However, there are still a lot of real world problems for which only small and noisy data sets exist. Hence, in this paper we focus on those small data sets of noisy images. Applying learning models to such data may not lead to the best possible results because of few and noisy training examples. We propose a hybrid neural network plait for improving the classification performance of state-of-the-art learning models applied to the images of such data sets. The improvement is reached by (1) using additionally to the images different further side information delivering different feature sets and requiring different learning models, (2) retraining all different learning models interactively within one common structure. The proposed hybrid neural network plait architecture reached in the experiments with 2 different data sets on average a classification performance improvement of 40% and 52% compared to a single convolutional neural network and 13% and 17% compared to a stacking ensemble method.
Keywords :
Big Data; image classification; learning (artificial intelligence); neural net architecture; HNNP; artificial intelligence; big data; classification performance improvement; hybrid neural network plait architecture; image classification; machine learning; Artificial neural networks; Biological neural networks; Ground penetrating radar; Multilayer perceptrons; Stacking; Training; convolutional neural network; hybrid neural network; image classification; multilayer perceptron; noisy data; side information; small data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Tools with Artificial Intelligence (ICTAI), 2013 IEEE 25th International Conference on
Conference_Location :
Herndon, VA
ISSN :
1082-3409
Print_ISBN :
978-1-4799-2971-9
Type :
conf
DOI :
10.1109/ICTAI.2013.15
Filename :
6735226
Link To Document :
بازگشت