Abstract
Applying computational intelligence techniques to create generative models of digits or alphabets has received somewhat little attention as compared to classification task. It is also more challenging to create a generative model that could successfully capture styles and detailed characteristics of symbols. In this paper, we describe the application of the Long Short-Term Memory (LSTM) model trained using a supervised learning approach for generating a variety of the letter A. LSTM is a recurrent neural network with a strong salient feature in its ability to handle long range dependencies, hence, it is a popular choice for building intelligent applications for speech recognition, conversation agent and other problems in time series domains. To formulate the problem as a generative task, all the pixels in a 2D image representing an alphabet (i.e., the letter A in this study) are flattened into a long vector to train the LSTM model. We have shown that LSTM has successfully learned to generate new letters A showing many coherent stylistic features with the original letters from the training sets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Hence, our predictive model can also be thought of as a binary classification model.
- 3.
References
Norman, D.A.: The Design of Everyday Things. MIT Press, London (2013)
Biederman, I.: Recognition-by-components: a theory of human image understanding. Psychol. Rev. 94(2), 115–147 (1987)
Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurones in cat’s striate cortex. Phisiology 148(3), 574–591 (1959)
Zeiler, M.D., Fergus, B.: Visualizing and understanding convolutional networks. In: Proceedings of the European Conference on Computer Vision (ECCV 2014), pp. 818–833 (2013)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Forgy, E.W.: Cluster analysis of multivariate data: efficiency versus interpretability of classifications. Biometrics 21, 768–769 (1965)
Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. http://arxiv.org/abs/1409.2329 (2015)
Arnheim, R.: Art and Visual Perception: A Psychology of the Creative Eye. University of California Press, London (1974)
Santoro, S.W.: Guide to Graphic Design. Pearson (2014)
Costello, V., Youngblood, S.A., Youngblood, N.E: Multimedia Foundations: Core Concepts for Digital Design, 2 edn. Focal Press (2013)
Pollen, D.A.: On the neural correlates of visual perception. Cereb. Cortex 9(1), 4–19 (1999)
Prucinkiewicz, P., Lindenmayer, A.: The Algorithmic Beauty of Plants. Springers, New York (1996)
Wolfram, S.: Cellular automata as models of complexity. Nature 331(4), 419–424 (1984)
Phon-Amnuaisuk, S., Panjapornpon, J.: Controlling generative processes of generative art. In: Proceedings of the International Neural Network Society Winter Conference (INNS-WC 2012). Procedia Computer Science, vol. 13, pp. 43–52 (2012)
Ariffin, M.K., Hadi, S., Phon-Amnuaisuk, S.: Evolving 3D models using interactive genetic algorithms and L-systems. In: Proceedings of the 11th International Workshop on Multi-disciplinary Trends in Artificial Intelligence (MIWAI 2017), pp. 485–493 (2017)
Goodfellow, I., Pouget-Abadie, J., Mehdi, M., Bing, X., Warde-Farley, D., Ozair, S., Courville, A., Bengio, J.: Generative adversarial networks. http://arxiv.org/abs/1406.2661 (2014)
Acknowledgments
We wish to thank anonymous reviewers for their comments that have helped improve this paper. We would like to thank the GSR office for their partial financial support given to this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Phon-Amnuaisuk, S., Salleh, N.D.H.M., Woo, SL. (2019). Pixel-Based LSTM Generative Model. In: Omar, S., Haji Suhaili, W., Phon-Amnuaisuk, S. (eds) Computational Intelligence in Information Systems. CIIS 2018. Advances in Intelligent Systems and Computing, vol 888. Springer, Cham. https://doi.org/10.1007/978-3-030-03302-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-03302-6_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03301-9
Online ISBN: 978-3-030-03302-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)