Artificial neural networks : an introduction / Kevin L. Priddy and Paul E. Keller.
- Bellingham, Wash. : SPIE, c2005.
- SPIE tutorial texts ; TT68.
Tutorial texts in optical engineering ; v. TT68
1 online resource (ix, 165 pages) : illustrations, digital file.
- Neural networks (Computer science)
- System Details:
- Mode of access: World Wide Web.
- This tutorial text provides the reader with an understanding of artificial neural networks (ANNs) and their application, beginning with the biological systems which inspired them, through the learning methods that have been developed and the data collection processes, to the many ways ANNs are being used today. The material is presented with a minimum of math (although the mathematical details are included in the appendices for interested readers), and with a maximum of hands-on experience. All specialized terms are included in a glossary. The result is a highly readable text that will teach the engineer the guiding principles necessary to use and apply artificial neural networks.
- Chapter 1. Introduction. 1.1. The neuron
1.2. Modeling neurons
1.3. The feedforward neural network
1.4. Historical perspective on computing with artificial neurons.
Chapter 2. Learning methods. 2.1. Supervised training methods
2.2. Unsupervised training methods.
Chapter 3. Data normalization. 3.1. Statistical or Z-score normalization
3.2. Min-max normalization
3.3. Sigmoidal or SoftMax normalization
3.4. Energy normalization
3.5. Principal components normalization.
Chapter 4. Data collection, preparation, labeling, and input coding. 4.1. Data collection
4.2. Feature selection and extraction.
Chapter 5. Output coding. 5.1. Classifier coding
5.2. Estimator coding.
Chapter 6. Post-processing.
Chapter 7. Supervised training methods. 7.1. The effects of training data on neural network performance
7.2. Rules of thumb for training neural networks
7.3. Training and testing.
Chapter 8. Unsupervised training methods. 8.1. Self-organizing maps (SOMs)
8.2. Adaptive resonance theory network.
Chapter 9. Recurrent neural networks. 9.1. Hopfield neural networks
9.2. The bidirectional associative memory (BAM)
9.3. The generalized linear neural network
9.4. Real-time recurrent network
9.5. Elman recurrent network.
Chapter 10. A plethora of applications. 10.1. Function approximation
10.2. Function approximation-Boston housing example
10.3. Function approximation-cardiopulmonary modeling
10.4. Pattern recognition-tree classifier example
10.5. Pattern recognition-handwritten number recognition example
10.6. Pattern recognition-electronic nose example
10.7. Pattern recognition-airport scanner texture recognition example
10.8. Self organization-serial killer data-mining example
10.9. Pulse-coupled neural networks-image segmentation example.
Chapter 11. Dealing with limited amounts of data. 11.1. K-fold cross-validation
11.2. Leave-one-out cross-validation
11.3. Jackknife resampling
11.4. Bootstrap resampling.
Appendix A. The feedforward neural network. A.1. Mathematics of the feedforward process
A.2. The backpropagation algorithm
A.3. Alternatives to backpropagation.
Appendix B. Feature saliency.
Appendix C. Matlab code for various neural networks. C.1. Matlab code for principal components normalization
C.2. Hopfield network
C.3. Generalized neural network
C.4. Generalized neural network example
C.5. ART-like network
C.6. Simple perceptron algorithm
C.7. Kohonen self-organizing feature map.
Appendix D. Glossary of terms
- "SPIE digital library."
Includes bibliographical references (pages -162) and index.
Title from PDF t.p. (viewed on 8/23/09).
- Keller, Paul E.
Society of Photo-optical Instrumentation Engineers.
- 9780819478726 (electronic)
- Publisher Number:
- 10.1117/3.633187 doi
- Access Restriction:
- Restricted for use by site license.
|Location||Notes||Your Loan Policy|
|Description||Status||Barcode||Your Loan Policy|