Abstract
In recent years, artificial intelligence has achieved remarkable progress by showing its applicable values in various industries. In the perspective of handling visual data, Convolutional Neural Network (CNN) and its derivative approaches are well known for their robustness and accuracy. However, as a neural network approach, CNN also has limitations. In exchange for good performance, CNN requires large amount of training data as well as heavy training process. The complex neural network layer design also needs to be reconstructed and tuned by experienced researches for different problems. Last but not least, the “curse of Blackbox”, a well-known disadvantage of neural network prevents CNN from providing reasonable explanation for the prediction results. All above limitations remind us that the most cutting-edge approach is still in the state of weak AI. In this paper, an approach called Abstractive Representation Model (ARM) is proposed which is different from the traditional neural network approaches. This goal of experimenting with such model is trying to address the CNN’s weaknesses and possibly developing a new way of handling image data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Wang, S.-C.: Artificial neural network. In: Wang, S.-C. (ed.) Interdisciplinary Computing in Java Programming, pp. 81–100. Springer, Boston (2003). https://doi.org/10.1007/978-1-4615-0377-4_5
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)
Albawi, S., Mohammed, T.A., Al-Zawi, S.: Understanding of a convolutional neural network. In: 2017 International Conference on Engineering and Technology (ICET), Antalya, pp. 1–6 (2017). https://doi.org/10.1109/ICEngTechnol.2017.8308186
Stathakis, D.: How many hidden layers and nodes? Int. J. Remote Sens. 30, 2133–2147 (2009). https://doi.org/10.1080/01431160802549278
Strong, A.I.: Artificial intelligence & associated technologies. Science [ETEBMS-2016] 5(6) (2016)
LeCun, Y., Cortes, C.: MNIST Handwritten Digit Database (2010)
O’Shea, K., Nash, R.: An Introduction to Convolutional Neural Networks. arXiv preprint arXiv:1511.08458 (2015)
Liu, B., Xia, Y., Yu, P.S.: Clustering through decision tree construction. In: Proceedings of the Ninth International Conference on Information and Knowledge Management, pp. 20–29, November 2000
Muda, Z., Yassin, W., Sulaiman, M.N., Udzir, N.I.: A K-Means and Naïve Bayes learning approach for better intrusion detection. Inf. Technol. J. 10(3), 648–655 (2011)
Teknomo, K.: K-Means clustering tutorial. Medicine 100(4), 3 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, X., Cohen, K. (2022). Abstractive Representation Modeling for Image Classification. In: Rayz, J., Raskin, V., Dick, S., Kreinovich, V. (eds) Explainable AI and Other Applications of Fuzzy Techniques. NAFIPS 2021. Lecture Notes in Networks and Systems, vol 258. Springer, Cham. https://doi.org/10.1007/978-3-030-82099-2_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-82099-2_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82098-5
Online ISBN: 978-3-030-82099-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)