Deep Leaky Single-peaked Triangle Neural Networks
Recently, Deep learning has made a great deal of success in processing images, audios, and natural languages and so on. The activation function is one of the key factors in Deep learning. In this paper, according to characteristics of biological neurons, an improved Leaky Single-Peaked Triangle Line...
Saved in:
Published in | International journal of control, automation, and systems Vol. 17; no. 10; pp. 2693 - 2701 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Bucheon / Seoul
Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers
01.10.2019
Springer Nature B.V 제어·로봇·시스템학회 |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Recently, Deep learning has made a great deal of success in processing images, audios, and natural languages and so on. The activation function is one of the key factors in Deep learning. In this paper, according to characteristics of biological neurons, an improved Leaky Single-Peaked Triangle Linear Unit (LSPTLU) activation function is presented for the right-hand response unbounded of Rectified Linear Unit (ReLU) and Leaky ReLU (LReLU). LSPTLU is more in line with the biological neuron essence and achieves the excellent performance of equivalent or beyond ReLU and LReLU on different datsets, e.g., MNIST, Fashion-MNIST, SVHN, IMAGENET, CALTECH101 and CIFAR10 datasets. |
---|---|
Bibliography: | http://link.springer.com/article/10.1007/s12555-018-0796-0 |
ISSN: | 1598-6446 2005-4092 |
DOI: | 10.1007/s12555-018-0796-0 |