Abstract
The aim of this paper is to provide some insight into designing a visual graph-shaped frontend for Keras and AutoKeras, two flagship deep learning software platforms. We also placed this particular endeavor in the larger context of deep learning mass adoption, which is just happening in many application fields, pointing out what challenges it is facing. There are several underlying conditions for going on quickly: automating the end-to-end machine learning pipeline, continuing the advances in GPU technology for supporting computing speed-up and parallelization, using tensor-enabled and GPU compatible mathematical libraries, and designing versatile GUIs capable of visually representing the network configuration in shape of a directed acyclic graph. All these blocks must be hierarchically stacked. Designing a Graph-Shaped frontend for deep learning platforms is the last, but equally essential brick to this construction and finally was the motivation behind this paper. Tensor-enabled libraries such as TensorFlow and the recent Nvidia GPU technology are the foundation layer. Keras successfully attempted to simplify the access to TensorFlow, while AutoKeras adds the automation support on top of Keras. Our proposed frontend, called Visual Keras&Autokeras, is attempting to visually emulate all the APIs related to Keras Functional model and AutoKeras AutoModel, in a codeless environment.
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
References
AutoKeras web site. https://autokeras.com/. Last accessed 28 May 2021
Haifeng, J., Qingquan, S., Xia, H.: Auto-Keras: An Efficient Neural Architecture Search System, arXiv:1806.10282 (2019)
Keras web site. https://keras.io/. Last accessed 28 May 2021
Google’s TensorFlow web site. https://www.TensorFlow.org/. Last accessed 28 May 2021
Elman, J.L.: Finding structure in time. Cogn. Sci. 14(2), 179–211 (1990)
Jordan, M.I.: Serial order: a parallel distributed processing approach. In: Neural-Network Models of Cognition – Biobehavioral Foundations. Advances in Psychology. Neural-Network Models of Cognition, vol. 121, pp. 471–495 (1997)
Williams, R.J., Hinton, G.E., Rumelhart, D.E.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Cho, K., et al.: Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation, arXiv:1406.1078 (2014)
LeCun, Y., et al.: Backpropagation Applied to Handwritten Zip Code Recognition. AT&T Bell Laboratories (1989)
Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195(1), 215–243 (1968)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Goodfellow, I., Bengio, Y., Courville. A.: Deep Learning, MIT Press (2016)
Zhang, W.: Shift-invariant pattern recognition neural network and its optical architecture. In: Proceedings of Annual Conference of the Japan Society of Applied Physics (1988)
Srivastava, N., Hinton, C.G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Ciresan, D., Meier, U., Gambardella, L., Schmidhuber, J.: Deep big simple neural nets for handwritten digit recognition. Neural Comput. 22(12), 3207–3220 (2010)
Google’s Cloud AutoML web site. https://cloud.google.com/automl. Last accessed 28 May 2021
Google’s Cloud AutoML docs web site. https://cloud.google.com/automl/docs. Last accessed 28 May 2021
TechCrunch web site. https://techcrunch.com/2018/01/17/googles-automl-lets-you-train-custom-machine-learning-models-without-having-to-code/. Last accessed 28 May 2021
Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. J. Mach. Learn. Res. 20(55), 1–21 (2019)
Křupala P.: Node Editor web site. https://pypi.org/project/nodeeditor/#description. Last accessed 28 May 2021
Keras Functional API web site. https://keras.io/guides/functional_api/. Last accessed 28 May 2021
AutoKeras AutoModel API web site. https://autokeras.com/tutorial/customized/. Last accessed 28 May 2021
Author information
Authors and Affiliations
Corresponding author
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
Georgescu, V., Gîfu, IA. (2022). Some Insight into Designing a Visual Graph-Shaped Frontend for Keras and AutoKeras, to Foster Deep Learning Mass Adoption. In: Rodríguez García, M.d.P., Cortez Alejandro, K.A., Merigó, J.M., Terceño-Gómez, A., Sorrosal Forradellas, M.T., Kacprzyk, J. (eds) Digital Era and Fuzzy Applications in Management and Economy. XX SIGEF 2021. Lecture Notes in Networks and Systems, vol 384. Springer, Cham. https://doi.org/10.1007/978-3-030-94485-8_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-94485-8_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-94484-1
Online ISBN: 978-3-030-94485-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)