Computational Advantages of Deep Prototype-Based Learning

被引：3

作者：

Hecht, Thomas ^{[1
]}

Gepperth, Alexander ^{[1
]}

机构：

[1] Univ Paris Saclay, Inria, Flowers Team, U2IS, 828 Blvd Marechaux, F-91762 Palaiseau, France

来源：

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II | 2016年 / 9887卷

关键词：

Prototype-based learning; Pattern recognition; Deep learning; Incremental learning;

D O I：

10.1007/978-3-319-44781-0_15

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：121 / 127

页数：7