1. Deep Reservoir Neural Networks for Trees.
- Author
-
Gallicchio, Claudio and Micheli, Alessio
- Subjects
- *
ARTIFICIAL neural networks , *CLOUD computing , *COMPUTER simulation , *ACCURACY of information , *COMPUTER vision - Abstract
Highlights • We show that is possible to have efficient deep learning for structured data. • We establish the Tree Echo State Property for Reservoir Computing extensions to trees. • We give empirical evidence of the benefit of multi-layered recursive architectures. • We improve efficiency and performance on molecules and document classification tasks. Abstract Tree structured data are a flexible tool to properly express many forms of hierarchical information. However, learning of such data through deep recursive models is particularly demanding. We will show through the introduction of the Deep Tree Echo State Network model (DeepTESN) that the randomized Neural Networks framework offers a formidable approach to allow an efficient treatment of learning in tree structured domains by deep architectures. Theoretical properties, for the Reservoir Computing setup constraints, and empirical behavior of the proposed approach are analyzed, showing its feasibility and accuracy. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF