ridm@nrct.go.th   ระบบคลังข้อมูลงานวิจัยไทย   รายการโปรดที่คุณเลือกไว้

A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks

หน่วยงาน Nanyang Technological University, Singapore

รายละเอียด

ชื่อเรื่อง : A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks
นักวิจัย : Xu, Zhao , Song, Qing , Wang, Danwei
คำค้น : DRNTU::Engineering::Electrical and electronic engineering::Electric power
หน่วยงาน : Nanyang Technological University, Singapore
ผู้ร่วมงาน : -
ปีพิมพ์ : 2557
อ้างอิง : Xu, Z., Song, Q., & Wang, D. (2014). A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks. Neural Computing and Applications, 24(7-8). 1851-1866. , http://hdl.handle.net/10220/20401 , http://dx.doi.org/10.1007/s00521-013-1436-5
ที่มา : -
ความเชี่ยวชาญ : -
ความสัมพันธ์ : Neural computing and applications
ขอบเขตของเนื้อหา : -
บทคัดย่อ/คำอธิบาย :

Training of recurrent neural networks (RNNs) introduces considerable computational complexities due to the need for gradient evaluations. How to get fast convergence speed and low computational complexity remains a challenging and open topic. Besides, the transient response of learning process of RNNs is a critical issue, especially for online applications. Conventional RNN training algorithms such as the backpropagation through time and real-time recurrent learning have not adequately satisfied these requirements because they often suffer from slow convergence speed. If a large learning rate is chosen to improve performance, the training process may become unstable in terms of weight divergence. In this paper, a novel training algorithm of RNN, named robust recurrent simultaneous perturbation stochastic approximation (RRSPSA), is developed with a specially designed recurrent hybrid adaptive parameter and adaptive learning rates. RRSPSA is a powerful novel twin-engine simultaneous perturbation stochastic approximation (SPSA) type of RNN training algorithm. It utilizes three specially designed adaptive parameters to maximize training speed for a recurrent training signal while exhibiting certain weight convergence properties with only two objective function measurements as the original SPSA algorithm. The RRSPSA is proved with guaranteed weight convergence and system stability in the sense of Lyapunov function. Computer simulations were carried out to demonstrate applicability of the theoretical results.

บรรณานุกรม :
Xu, Zhao , Song, Qing , Wang, Danwei . (2557). A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks.
    กรุงเทพมหานคร : Nanyang Technological University, Singapore.
Xu, Zhao , Song, Qing , Wang, Danwei . 2557. "A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks".
    กรุงเทพมหานคร : Nanyang Technological University, Singapore.
Xu, Zhao , Song, Qing , Wang, Danwei . "A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks."
    กรุงเทพมหานคร : Nanyang Technological University, Singapore, 2557. Print.
Xu, Zhao , Song, Qing , Wang, Danwei . A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks. กรุงเทพมหานคร : Nanyang Technological University, Singapore; 2557.