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.
[1]
Eibe Frank,et al.
Introducing Machine Learning Concepts with WEKA
,
2016,
Statistical Genomics.
[2]
Gaël Varoquaux,et al.
Scikit-learn: Machine Learning in Python
,
2011,
J. Mach. Learn. Res..
[3]
Kevin Leyton-Brown,et al.
Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms
,
2012,
KDD.
[4]
Keon Myung Lee,et al.
Autonomicity Levels and Requirements for Automated Machine Learning
,
2017,
RACS.
[5]
Sean Davis,et al.
Statistical Genomics. Methods and Protocols.
,
2016,
Anticancer research.
[6]
Trevor Darrell,et al.
Caffe: Convolutional Architecture for Fast Feature Embedding
,
2014,
ACM Multimedia.
[7]
Yuan Yu,et al.
TensorFlow: A system for large-scale machine learning
,
2016,
OSDI.