ABSTRACT
In recent years, deep neural networks are active in numerous applications such as predictive, advertising and healthcare applications using of image, voice and text recognitions. However, deep neural networks are useful methods but usually require a proper modeling to construct a deep neural network method in any application. Designing a model is a tedious task to be realized in the network, which opens an issue to design an effective software tool for modeling deep neural networks. To get an excellent model for deep neural networks, the developers should have sufficient understanding and experience for deep neural network methods. The developers also require coding skills with the deep learning frameworks and knowledge for the computing resources. This paper presents a software tool based on a Graphical User Interface (GUI) to develop deep neural network models, which train the models with external computing resources and automate the hyper-parameter tuning.
- A. Martín, et al., "TensorFlow: A System for Large-Scale Machine Learning," Operating Systems Design and Implementation, Vol. 16, pp. 265--283, 2016. Google ScholarDigital Library
- J. Yangqing, et al., "Caffe: Convolutional Architecture for Fast Feature Embedding," Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675--678, 2014. Google ScholarDigital Library
- Keras, https://keras.io/ (accessed on April, 05, 2018)Google Scholar
- T. C. Smith and E. Frank, Statistical Genomics: Methods and Protocols. New York, NY: Springer, 2016, ch. Introducing Machine Learning Concepts with WEKA, pp. 353--378.Google Scholar
- https://spark.apache.org/docs/latest/ml-guide.htmlGoogle Scholar
- K. M. Lee, K. I. Kim, J. Yoo, Autonomicity Levels and Requirements for Automated Machine Learning. RACS 2017, pp. 46--48, 2017. Google ScholarDigital Library
- P. Fabian, et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, pp. 2825--2830, 2011. Google ScholarDigital Library
- Keon Myung Lee, Jaesoo Yoo, Jiman Hong, Autonomicity Levels and Requirements for Automated Machine Learning. In Proceedings of the International Conference on Research in Adaptive and Convergent Systems (pp. 46--48), 2017. Google ScholarDigital Library
- Theano, http://deeplearning.net/software/theano/ (accessed on April, 05, 2018).Google Scholar
- Thornton, C., Hutter, F., Hoos, H. H., Leyton-Brown, K. Auto-WEKA: Combined selection and hyperparameter optimization of classification algorithms. In Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 847--855). ACM, 2013. Google ScholarDigital Library
Index Terms
- A deep learning model generation method for code reuse and automatic machine learning
Recommendations
Differentiable neural architecture learning for efficient neural networks
Highlights- We build a new standalone control module based on the scaled sigmoid function to enrich the neural network module family to enable the neural architecture ...
AbstractEfficient neural networks has received ever-increasing attention with the evolution of convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems to ...
Deep learning: an overview and main paradigms
In the present paper, we examine and analyze main paradigms of learning of multilayer neural networks starting with a single layer perceptron and ending with deep neural networks, which are considered regarded as a breakthrough in the field of the ...
Comments