Reading directions
Below are some hints on the reading material. It is intended to give
pointers to chapters of the books where you can start reading. It is thus not a complete and exhaustive reading guide to all you need to
know.
* means
it is not covered in the book. You may then either read some of the
additional material given in the Lecture notes folder (RBFs,
reinforcement learning) and/or
chapters in the free book by Rojas.
Marsland: Machine Learning, an Algorithmic Perspective
One layer perceptron 2.2-2.3
Multi layer perceptron 3.1-3.2, 3.6
Generalization 3.3
Principal component analysis, independent component analysis 10.2,
10.4
Self organizing maps, vector quantization 9.2-9.3
Boltzmann machines, Hopfield nets, Temporal nets 11.6, *
Regularization 3.3, 8.1-8.2
Radial basis functions 4.1-4.3,
Reinforcement learning 13.1-13.6
Fausett: Fundamentals of Neural Networks
One layer perceptron 1.6, 2.1-2.3, 3.1-3.3
Multi layer perceptron 6
Generalization 6.2
Principal component analysis, independent component analysis *
Self organizing maps, vector quantization 4.1-4.3
Boltzmann machines, Hopfield nets, Temporal nets 3.4, 7.1-7.2
Regularization *
Radial basis functions *
Reinforcement learning *
Rojas: Neural Networks - A Systematic Introduction
One layer perceptron 3.1-3.3, 4.1-4.2,
Multi layer perceptron 7.1-7.3
Generalization 9.1
Principal component analysis, independent component analysis 5.3
Self organizing maps, vector quantization 5.1, 15
Boltzmann machines, Hopfield nets, Temporal nets 12.1-12.2,
13.1-13.4, 14
Regularization 9.1-9.2, 8.5
Radial basis functions 16.2.5
Reinforcement learning *