The book explains and deduces mathematically the working principle of many architectures, and presents commented examples (good ones) in structured English (very similar to Pascal). I used it as the basis for many NN's and felt quite satisfied in all cases.
The appearance of digital computers and the development of modern theories
of learning and neural processing both occurred at about the same time, during
the late 1940s. Since that time, the digital computer has been used as a tool
to model individual neurons as well as clusters of neurons, which are called
neural networks. A large body of neurophysiological research has accumulated
since then. For a good review of this research, see Neural and Brain Modeling
by Ronald J. MacGregor . The study of artificial neural systems (ANS) on
computers remains an active field of biomedical research.
Our interest in this text is not primarily neurological research. Rather, we
wish to borrow concepts and ideas from the neuroscience field and to apply them
to the solution of problems in other areas of science and engineering. The ANS
models that are developed here may or may not have neurological relevance.
Therefore, we have broadened the scope of the definition of ANS to include
models that have been inspired by our current understanding of the brain, but
that do not necessarily conform strictly to that understanding.