✦ LIBER ✦

A recurrent neural network: Limitations and training

✍ Scribed by Esther Levin

Publisher: Elsevier Science
Year: 1990
Tongue: English
Weight: 790 KB
Volume: 3
Category: Article
ISSN: 0893-6080
DOI: 10.1016/0893-6080(90)90054-o

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Computational limitations on training si

Computational limitations on training sigmoid neural networks

✍ Klaus-Uwe Höffgen 📂 Article 📅 1993 🏛 Elsevier Science 🌐 English ⚖ 475 KB

Training fully recurrent neural networks

Training fully recurrent neural networks on a ring transputer array

✍ G Kechriotis; ES Manolakos 📂 Article 📅 1994 🏛 Elsevier Science 🌐 English ⚖ 604 KB

Bispectrum estimation using a recurrent

Bispectrum estimation using a recurrent neural network

✍ Takehiko Ogawa; Yukio Kosugi 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 202 KB 👁 2 views

Techniques using FFT have been used widely in the past for bispectrum estimation. However, when FFT was used for bispectrum estimation of data with many points, there was a problem of escalated level of calculation, making applications to real problems requiring real-time processing such as image pr

Recurrent neural networks can be trained

Recurrent neural networks can be trained to be maximum a posteriori probability classifiers

✍ Simone Santini; Alberto Del Bimbo 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 390 KB

Network restoration using recurrent neur

Network restoration using recurrent neural networks

✍ G. Prem Kumar; P. Venkataram 📂 Article 📅 1998 🏛 John Wiley and Sons 🌐 English ⚖ 212 KB 👁 2 views

A method for training recurrent neural n

A method for training recurrent neural networks for classification by building basins of attraction

✍ Roelof K. Brouwer 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 644 KB

The main contribution of this report is the suggestion, development, and trial of a new way of using a Hopfield network for classification. Rather than storing the members of the training sets (sets of exemplars) as stable points, a connection matrix is determined, using perceptron-type learning, su