Computational Advantages of Deep Prototype-Based Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Computational Advantages of Deep Prototype-Based Learning

Thomas Hecht


We present a deep prototype-based learning architecture which achieves a performance that is competitive to a conventional, shallow prototype-based model but at a fraction of the computational cost, especially w.r.t. memory requirements. As prototype-based classification and regression methods are typically plagued by the exploding number of prototypes necessary to solve complex problems, this is an important step towards efficient prototype-based classification and regression. We demonstrate these claims by benchmarking our deep prototype-based model on the well-known MNIST dataset.
Fichier principal
Vignette du fichier
article_ICANN16.pdf (1.23 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01418135 , version 1 (16-12-2016)



Thomas Hecht, Alexander Gepperth. Computational Advantages of Deep Prototype-Based Learning. International Conference on Artificial Neural Networks (ICANN), 2016, Barcelona, Spain. pp.121 - 127, ⟨10.1007/978-3-319-44781-0_15⟩. ⟨hal-01418135⟩
105 View
270 Download



Gmail Facebook Twitter LinkedIn More