A compact network learning model for distribution regression. (February 2019)

• Record Type: Journal Article
• Authors: Kou, Connie Khor Li; Lee, Hwee Kuan; Ng, Teck Khim
• Is Part Of: Neural networks. Volume 110(2019)
• Page Start: 199
• Page End: 212
• Publication Date: 2019-02
• Subjects: Supervised learning -- Distribution regression; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2018.12.007
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces. In particular, neural networks are unable to encode function inputs compactly as each node encodes just a real value. We propose a novel idea to address this shortcoming: to encode an entire function in a single network node. To that end, we design a compact network representation that encodes and propagates functions in single nodes for the distribution regression task. Our proposed distribution regression network (DRN) achieves higher prediction accuracies while using fewer parameters than traditional neural networks.