• Recurrent Neural Networks: Design and Applications (The Crc Press International Series on Computational Intelligence)
• Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry and Engineering
• Pattern Recognition and Machine Learning (Information Science and Statistics)
• The Elements of Statistical Learning

I should buy it in 2001.
Review written by: Valentine Dvorovkin From
I give this book 5 stars. It is a must have book, very well written. It has good balance between rigorous theory and authors reasonong regarding the subject.
I'm not a beginner in this field, and still I found a lot of interesting ideas, that can help not only to improve quality of the net, but also make you see "bigger picture".

Unexpected insights that make you go: "Aha!"
Review written by: Temujin Gautama From Belgium
"Recurrent Neural Networks for Prediction: Learning Algorithms,
Architectures and Stability," approaches the field of recurrent neural networks from both a practical and a theoretical perspective. Starting from the fundamentals, where unexpected insights are offered even at the level of the dynamical richness of simple neurons, the authors describe many existing algorithms and gradually introduce novel ones. The latter are convicingly shown to yield better prediction performances than traditional approaches, when applied to real-world data. They also dedicate a considerable amount of time on the (practical) issue of nonlinearity analysis of time series, which is or should be, indeed, the cradle of all proper modelling and/or filtering solutions: nonlinearity should be assessed prior to choosing the appropriate model and/or filters, since linear ones are to be preferred if sufficient for the problem. I would recommend this book to any researcher who is active in the field of recurrent neural networks and time series analysis, but also to researchers who are new in the field, since the book offers an extensive overview of the current state-of-the-art approaches.