Augmented Efficient BackProp for Backpropagation Learning in Deep Autoassociative Neural Networks

被引：0

作者：

Embrechts, Mark J. ^{[1
]}

Hargis, Blake J. ^{[1
]}

Linton, Jonathan D. ^{[2
]}

机构：

[1] Rensselaer Polytech Inst, Dept Ind & Syst Engn, Troy, NY 12180 USA

[2] Univ Ottawa, Sch Management, Ottawa, ON K1N 6N5, Canada

来源：

2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010 | 2010年

基金：

加拿大自然科学与工程研究理事会;

关键词：

PRINCIPAL COMPONENT ANALYSIS; NONLINEAR PCA; ALGORITHM;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We introduce Augmented Efficient BackProp as a strategy for applying the backpropagation algorithm to deep autoencoders, i.e., autoassociators with many hidden layers, without relying on a weight initialization using restricted Boltzmann machines. This training method is an extension of Efficient BackProp, first proposed by LeCun et al. [1], and is benchmarked on three different types of application datasets.

引用

页数：6

共 50 条

[21] Dynamics of autoassociative neural networks
Morinaga, S
Yoshizawa, S
PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 233 - 236
[22] Training Deep Spiking Neural Networks Using Backpropagation
Lee, Jun Haeng
Delbruck, Tobi
Pfeiffer, Michael
FRONTIERS IN NEUROSCIENCE, 2016, 10
[23] On impulsive autoassociative neural networks
Guan, ZH
Lam, J
Chen, GR
NEURAL NETWORKS, 2000, 13 (01) : 63 - 69
[24] Stable tensor neural networks for efficient deep learning
Newman, Elizabeth
Horesh, Lior
Avron, Haim
Kilmer, Misha E.
FRONTIERS IN BIG DATA, 2024, 7
[25] Memory-Efficient Backpropagation for Recurrent Neural Networks
Ayoub, Issa
Al Osman, Hussein
ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, 11489 : 274 - 283
[26] Deep Generative Stochastic Networks Trainable by Backprop
Bengio, Yoshua
Thibodeau-Laufer, Eric
Alain, Guillaume
Yosinski, Jason
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), 2014, 32 : 226 - 234
[27] Concept learning through deep reinforcement learning with memory-augmented neural networks
Shi, Jing
Xu, Jiaming
Yao, Yiqun
Xu, Bo
NEURAL NETWORKS, 2019, 110 : 47 - 54
[28] The interchangeability of learning rate and gain in backpropagation neural networks
Thimm, G
Moerland, P
Fiesler, E
NEURAL COMPUTATION, 1996, 8 (02) : 451 - 460
[29] IMPROVING BACKPROPAGATION LEARNING USING AUXILIARY NEURAL NETWORKS
FORTUNA, L
GRAZIANI, S
LOPRESTI, M
MUSCATO, G
INTERNATIONAL JOURNAL OF CONTROL, 1992, 55 (04) : 793 - 807
[30] A general backpropagation algorithm for feedforward neural networks learning
Yu, XH
Efe, MO
Kaynak, O
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (01): : 251 - 254

← 1 2 3 4 5 →