Deep Learning and Developmental Learning: Emergence of Fine-to-Coarse Conceptual Categories at Layers of Deep Belief Network. (September 2016)

• Record Type: Journal Article
• Authors: Sadeghi, Zahra
• Is Part Of: Perception. Volume 45:Number 9(2016)
• Page Start: 1036
• Page End: 1045
• Publication Date: 2016-09
• Subjects: deep learning -- developmental learning -- deep representation -- levels of abstraction; Perception -- Periodicals; Perception -- Periodicals; Perception; Periodicals; 153.705
• DOI: 10.1177/0301006616651950
• Languages: English
• ISSNs: 0301-0066

Abstract

In this paper, I investigate conceptual categories derived from developmental processing in a deep neural network. The similarity matrices of deep representation at each layer of neural network are computed and compared with their raw representation. While the clusters generated by raw representation stand at the basic level of abstraction, conceptual categories obtained from deep representation shows a bottom-up transition procedure. Results demonstrate a developmental course of learning from specific to general level of abstraction through learned layers of representations in a deep belief network.