Learning with Recurrent Neural Networks

ISBN-13: 9781852333430 / Angielski / Miękka / 2000 / 150 str.

Barbara Hammer; B. Hammer

Opis

Folding networks, a generalization of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. After wards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated - including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes.

Spis treści

Recurrent and folding networks.- Approximation ability.- Learnability.- Complexity.- Conclusion.