✦ LIBER ✦

Adaptive incremental learning in neural networks

✍ Scribed by Abdelhamid Bouchachia; Nadia Nedjah

Publisher: Elsevier Science
Year: 2011
Tongue: English
Weight: 81 KB
Volume: 74
Category: Article
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2010.12.018

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Adaptive optimization in neural networks

✍ K.Y.M. Wong; D. Sherrington 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 202 KB

We apply the principle of adaptation to optimize the performance of neural networks with (i) noisy retrieval and (ii) disruptive dilution. ## I. Introduction Learning in neural networks can be described as a search procedure in the space of the adjustable synaptic weights. A performance function

Incremental learning with multi-level ad

Incremental learning with multi-level adaptation

✍ Abdelhamid Bouchachia 📂 Article 📅 2011 🏛 Elsevier Science 🌐 English ⚖ 847 KB

Self-adaptation is an inherent part of any natural and intelligent system. Specifically, it is about the ability of a system to reconcile its requirements or goal of existence with the environment it is interacting with, by adopting an optimal behavior. Self-adaptation becomes crucial when the envir

Adaptive active appearance model with in

Adaptive active appearance model with incremental learning

✍ Jaewon Sung; Daijin Kim 📂 Article 📅 2009 🏛 Elsevier Science 🌐 English ⚖ 782 KB

Automatic learning in chaotic neural net

Automatic learning in chaotic neural networks

✍ Masataka Watanabe; Kazuyuki Aihara; Shunsuke Kondo 📂 Article 📅 1996 🏛 John Wiley and Sons 🌐 English ⚖ 445 KB 👁 1 views

Learning from hints in neural networks

✍ Yaser S Abu-Mostafa 📂 Article 📅 1990 🏛 Elsevier Science 🌐 English ⚖ 383 KB

A dynamic optimization approach for adap

A dynamic optimization approach for adaptive incremental learning

✍ Marcelo N. Kapp; Robert Sabourin; Patrick Maupin, 📂 Article 📅 2011 🏛 John Wiley and Sons 🌐 English ⚖ 448 KB

A fundamental problem when performing incremental learning is that the best set of a classification system's parameters can change with the evolution of the data. Consequently, unless the system self-adapts to such changes, it will become obsolete, even if the application environment seems to be sta