✦ LIBER ✦

Learning long-term dependencies with recurrent neural networks

✍ Scribed by Anton Maximilian Schaefer; Steffen Udluft; Hans-Georg Zimmermann

Book ID: 113815739
Publisher: Elsevier Science
Year: 2008
Tongue: English
Weight: 422 KB
Volume: 71
Category: Article
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2007.12.036

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Learning long-term dependencies by the s

Learning long-term dependencies by the selective addition of time-delayed connections to recurrent neural networks

✍ Romuald Boné; Michel Crucianu; Jean-Pierre Asselin de Beauville 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 246 KB

How embedded memory in recurrent neural

How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies

✍ Tsungnan Lin; Bill G. Horne; C.Lee Giles 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 202 KB

Learning long-term temporal dependencies with recurrent neural networks can be a difficult problem. It has recently been shown that a class of recurrent neural networks called NARX networks perform much better than conventional recurrent neural networks for learning certain simple long-term dependen

Stable reinforcement learning with recur

Stable reinforcement learning with recurrent neural networks

✍ James Nate Knight; Charles Anderson 📂 Article 📅 2011 🏛 South China University of Technology and Academy o 🌐 English ⚖ 375 KB

Learning in recurrent neural networks

✍ Halbert White 📂 Article 📅 1991 🏛 Elsevier Science 🌐 English ⚖ 85 KB

Bayesian learning for recurrent neural n

Bayesian learning for recurrent neural networks

✍ Michel Crucianu; Romuald Boné; Jean-Pierre Asselin de Beauville 📂 Article 📅 2001 🏛 Elsevier Science 🌐 English ⚖ 126 KB

Recurrent neural network with short-term

Recurrent neural network with short-term memory and fast structural learning method

✍ Shinichi Kikuchi; Masakazu Nakanishi 📂 Article 📅 2003 🏛 John Wiley and Sons 🌐 English ⚖ 849 KB

## Abstract The Elman network is used frequently in learning time series. However, it has several problems: (1) a comparatively long learning time, (2) learning is not necessarily successful, (3) lack of discussions on a generalization ability, and (4) the necessity of deciding unit numbers and the