Regular price
43.750 KD
inc. VAT
Couldn't load pickup availability
Table of contents
- Contentsv
- Forewordix
- Chapter 1. Introduction1
- 1.1 Neural computing–today's perspective1
- 1.2 The purpose of this book2
- 1.3 A brief overview3
- 1.4 Acknowledgements3
- Chapter 2. Mathematical background for neural computing5
- 2.1 Introduction5
- 2.2 Why neural networks?5
- 2.3 Brief historical background6
- 2.4 Pattern recognition8
- 2.5 Pattern classification8
- 2.6 The single-layer perceptron9
- 2.7 From the 1960s to today: multi-layer networks12
- 2.8 Multi-layer perceptrons and the error back-propagation algorithm14
- 2.9 Training a multi-layer perceptron16
- 2.10 Probabilistic interpretation of network outputs18
- 2.11 Unsupervised learning–the motivation19
- 2.12 Cluster analysis20
- 2.13 Clustering algorithms21
- 2.14 Data visualisation-Kohonen's feature map24
- 2.15 From the feature map to classification27
- 2.16 Radial Basis Function networks28
- 2.17 Training an RBF network30
- 2.18 Comparison between RBF networks and MLPs31
- 2.19 Auto-associative neural networks32
- 2.20 Recurrent networks33
- 2.21 Conclusion35
- Chapter 3. Managing a neural computing project37
- 3.1 Introduction37
- 3.2 Neural computing projects are different37
- 3.3 The project life cycle38
- 3.4 Project planning39
- 3.5 Project monitoring and control42
- 3.6 Reviewing43
- 3.7 Configuration management44
- 3.8 Documentation45
- 3.9 The deliverable system46
- Chapter 4. Identifying applications and assessing their feasibility49
- 4.1 Introduction49
- 4.2 Identifying neural computing applications50
- 4.3 Typical examples of neural computing applications51
- 4.4 Preliminary assessment of candidate application53
- 4.5 Technical feasibility53
- 4.6 Data availability and cost of collection54
- 4.7 The business case55
- 4.8 Conclusion57
- Chapter 5. Neural computing hardware and software59
- 5.1 Introduction59
- 5.2 Computational requirements59
- 5.3 Platforms for software solutions61
- 5.4 Special-purpose hardware64
- 5.5 Deliverable system66
- Chapter 6. Collecting and preparing data67
- 6.1 Introduction67
- 6.2 Glossary67
- 6.3 Data requirements68
- 6.4 Data collection and data understanding71
- Chapter 7. Design, training and testing of the prototype77
- 7.1 Introduction77
- 7.2 Overview of design77
- 7.3 Pre-processing79
- 7.4 Input/output encoding82
- 7.5 Selection of neural network type87
- 7.6 Selection of neural network architecture88
- 7.7 Training and testing the prototype89
- 7.8 From prototype to deliverable system94
- 7.9 Common problems in training and/or testing the prototype95
- Chapter 8. The case studies99
- 8.1 Overview of the case studies99
- 8.2 Benchmark results102
- 8.3 Application of data visualisation to the case studies104
- 8.4 Application of MLPs to the case studies109
- 8.5 Application of RBF networks to the case studies116
- 8.6 Conclusions119
- Chapter 9. More advanced topics121
- 9.1 Introduction121
- 9.2 Data visualisation121
- 9.3 Multi-layer perceptrons123
- 9.4 On-line learning125
- 9.5 Introduction to Netlab126
- Appendix A: The error back-propagation algorithm for weight updates in an MLP129
- Appendix B: Use of Bayes' theorem to compensate for different prior probabilities131
- References133
- Index137
Book details
- Vendor Elsevier S & T
- SKU 9780340705896
- ISBN-13 9780080512600
- Author Tarassenko, Lionel
- Category Computers
- Subject Interactive & Multimedia
Do you have questions about this book?
Neural networks have shown enormous potential for commercial exploitation over the last few years but it is easy to overestimate their capabilities. A few simple algorithms will learn relationships between cause and effect or organise large volumes of data into orderly and informative patterns but they cannot solve every problem and consequently their application must be chosen carefully and appropriately.
This book outlines how best to make use of neural networks. It enables newcomers to the technology to construct robust and meaningful non-linear models and classifiers and benefits the more experienced practitioner who, through over familiarity, might otherwise be inclined to jump to unwarranted conclusions. The book is an invaluable resource not only for those in industry who are interested in neural computing solutions, but also for final year undergraduates or graduate students who are working on neural computing projects. It provides advice which will help make the best use of the growing number of commercial and public domain neural network software products, freeing the specialist from dependence upon external consultants.
This book outlines how best to make use of neural networks. It enables newcomers to the technology to construct robust and meaningful non-linear models and classifiers and benefits the more experienced practitioner who, through over familiarity, might otherwise be inclined to jump to unwarranted conclusions. The book is an invaluable resource not only for those in industry who are interested in neural computing solutions, but also for final year undergraduates or graduate students who are working on neural computing projects. It provides advice which will help make the best use of the growing number of commercial and public domain neural network software products, freeing the specialist from dependence upon external consultants.
Instant delivery by email
Your access email arrives within minutes of checkout, with a sign-in link for each book — no shipping, no waiting.
Read on any device
Books open in VitalSource Bookshelf on your phone, tablet, or computer, online or offline. Your library is always available at aafaq.vitalsource.com — just log in with the email you used at checkout.
Lost the email?
Resend it to yourself in seconds from My eBook orders, or email cs@aafaqeducation.com and we'll help.