✦ LIBER ✦

The computational intractability of training sigmoidal neural networks

✍ Scribed by Jones, L.K.

Book ID: 114540592
Publisher: IEEE
Year: 1997
Tongue: English
Weight: 754 KB
Volume: 43
Category: Article
ISSN: 0018-9448
DOI: 10.1109/18.567673

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

The Dynamic Universality of Sigmoidal Ne

The Dynamic Universality of Sigmoidal Neural Networks

✍ Joe Kilian; Hava T. Siegelmann 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 428 KB

Subset-based training and pruning of sig

Subset-based training and pruning of sigmoid neural networks

✍ Guian Zhou; J. Si 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 170 KB

In the present paper we develop two algorithms, subset-based training (SBT) and subset-based training and pruning (SBTP), using the fact that the Jacobian matrices in sigmoid network training problems are usually rank deficient. The weight vectors are divided into two parts during training, accordin

On learning of Sigmoid Neural Networks

✍ Kayvan Najarian 📂 Article 📅 2001 🏛 John Wiley and Sons 🌐 English ⚖ 149 KB

On the computational efficiency of symme

On the computational efficiency of symmetric neural networks

✍ Juraj Wiedermann 📂 Article 📅 1991 🏛 Elsevier Science 🌐 English ⚖ 542 KB

Constructive training of probabilistic n

Constructive training of probabilistic neural networks

✍ Michael R. Berthold; Jay Diamond 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 292 KB