1. Deep hybrid neural-kernel networks using random Fourier features
- Author
-
Siamak Mehrkanoon and Johan A. K. Suykens
- Subjects
Optimization problem ,Computer science ,Cognitive Neuroscience ,Explicit feature mapping ,02 engineering and technology ,010501 environmental sciences ,01 natural sciences ,Kernel (linear algebra) ,Artificial Intelligence ,0202 electrical engineering, electronic engineering, information engineering ,Feature (machine learning) ,0105 earth and related environmental sciences ,Block (data storage) ,Artificial neural network ,business.industry ,Deep learning ,Kernel methods ,Computer Science Applications ,Hybrid models ,Kernel method ,Kernel (statistics) ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,Algorithm ,Neural networks - Abstract
This paper introduces a novel hybrid deep neural kernel framework. The proposed deep learning model makes a combination of a neural networks based architecture and a kernel based model. In particular, here an explicit feature map, based on random Fourier features, is used to make the transition between the two architectures more straightforward as well as making the model scalable to large datasets by solving the optimization problem in the primal. Furthermore, the introduced framework is considered as the first building block for the development of even deeper models and more advanced architectures. Experimental results show an improvement over shallow models and the standard non-hybrid neural networks architecture on several medium to large scale real-life datasets. (C) 2018 Elsevier B.V. All rights reserved.
- Published
- 2018