✦ LIBER ✦

Multiobjective Hybrid Optimization and Training of Recurrent Neural Networks

✍ Scribed by Delgado, M.; Cuellar, M.P.; Pegalajar, M.C.

Book ID: 117938786
Publisher: IEEE
Year: 2008
Tongue: English
Weight: 633 KB
Volume: 38
Category: Article
ISSN: 1083-4419
DOI: 10.1109/tsmcb.2007.912937

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Constructive training of recurrent neura

Constructive training of recurrent neural networks using hybrid optimization

✍ Niranjan Subrahmanya; Yung C. Shin 📂 Article 📅 2010 🏛 Elsevier Science 🌐 English ⚖ 1010 KB

Training recurrent neural networks using

Training recurrent neural networks using a hybrid algorithm

✍ Mounir Ben Nasr; Mohamed Chtourou 📂 Article 📅 2010 🏛 Springer-Verlag 🌐 English ⚖ 606 KB

Recurrent Neural Networks for Structural

Recurrent Neural Networks for Structural Optimization

✍ Azadeh Parvin; Gursel Serpen 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 130 KB

A recurrent neural network: Limitations

A recurrent neural network: Limitations and training

✍ Esther Levin 📂 Article 📅 1990 🏛 Elsevier Science 🌐 English ⚖ 790 KB

Training feedforward neural networks usi

Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm

✍ SeyedAli Mirjalili; Siti Zaiton Mohd Hashim; Hossein Moradian Sardroudi 📂 Article 📅 2012 🏛 Elsevier Science 🌐 English ⚖ 634 KB

Hybrid interior point training of modula

Hybrid interior point training of modular neural networks

✍ Peter T. Szymanski; Michael Lemmon; Christopher J. Bett 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 571 KB

Modular neural networks use a single gating neuron to select the outputs of a collection of agent neurons. Expectation-maximization (EM) algorithms provide one way of training modular neural networks to approximate non-linear functionals. This paper introduces a hybrid interior-point (HIP) algorithm