 "Catching up with your research..." | 2008-10-11 |
| - Reviewed By Business Technology Strategist from Washington DC, USA |
| For those fascinated with Neural Network Theory, this book is a comprehensive compendium of some of the best papers published in the subject. So far it is one of the best volumes in Neural Networks that I have seen, and a well thought paper compilation. |
| |
| "Excellent reference work on brain theory" | 2007-01-05 |
| - Reviewed By fygar from hermosa beach, ca |
| The articles in this work are written by a who's who list of authors from the cognitive and computational neuroscience community. Each article is useful for getting an initial bearing on a topic from this dynamic field. The references for each article serve as useful "jumping off points" for further learning. It should be noted that this text is not a typical college textbook -- it is a reference work. As such, a beginner to the field should consider one of the other introductory textbooks (perhaps "The Cognitive Neurosciences"). |
| |
 "Misleading title, a useful book otherwise" | 2005-01-04 |
| - Reviewed By Skirmantas Janusonis from United States |
Look through this book to convince yourself that an exact brain theory does not exist. The arrangement of the articles by the first letter of their title tells it all (consider classifying animals by the first letter of their name). The editors wrongly assume that mathematical methods equal theory; actually, theory is a small conceptual tent under which a large number of experimentally established facts can be gathered. In most cases, mathematics is a very useful tool in pitching this tent, but it has little to do with the tent itself.
An exact theory of the brain may be possible and we are in dire need of it. Unfortunately, nobody has come up with it yet. This book is an encyclopedia of various mathematical methods that have been used to solve various neuroscience problems. These methods and solutions are as diverse as the problems themselves. Don't look for common themes in this book. If you are looking for a unified brain theory, you'll be much better off reading standard neuroscience textbooks. I do hope one day we'll be able to cast these vague ideas into something precise and, most likely, mathematical. Sadly, not today. I own a copy of this book and use it to remind me why and how we have failed so far.
It should be kept in mind that it is not at all clear that "neural" networks can emulate consciousness. They may or they may not. Firstly, a single neuron resembles a computer processor in its complexity and is a constantly evolving entity. Secondly, only 10% of brain cells are neurons and the remaining 90% (glial cells) now too appear to be involved in information processing. At a more fundamental level, consciousness may be less algorithmic and computational than we expect. Finally, the brain and the reality "outside the brain" are a two-way street. As the great neuroscientist Cajal put it, "As long as our brain remains an arcanum, the Universe, a reflection of its structure, will also be a mystery". If we assume the brain analyzes something, we need to define a reality independent of this analysis -- a hardly possible task if standard "input-output" approaches are used.
If the title of this book were "Current Mathematical Methods in Neurosciences", I'd have no problem giving it five stars.
November 2005: The chapters in the second edition are still arranged alphabetically. I refuse to believe neuro-mathematicians cannot think more coherently.
One final note for those looking for serious conceptual advances on the theoretical front: do no miss "Spikes: Exploring the Neural Code" (edited by F. Rieke) and "Decisions, Uncertainty, and the Brain: The Science of Neuroeconomics" by Paul Glimcher. |
| |
| "Basic science for consciousness" | 2001-10-10 |
| - Reviewed By Anonymous |
| Research is tedious, but if you want to know the nitty-gritty of mind-brain theory and neural networking, this book is an invaluable resource for basic, relevant, and accessible papers on the subjects. Encompassing seminal works from an unusually broad range of disciplines, here is an outstanding reference for those concerned with the mechanisms of intelligence. |
| |
| "Excellent compilation" | 2001-06-03 |
| - Reviewed By Dr. Lee D. Carlson from Baltimore, Maryland USA |
| This complilation of articles by leading experts in the field gives an excellent overview of studies in cognitive theory and the theory and applications of neural networks. The first two parts of the book give an overview and background of the properties of neurons and gives guidance to the reader on what sequence the articles are to be read. I did not read all of the articles, but only those that piqued my interest. I found the following articles particularly well-written and informative: 1. "Applications of Neural Networks": Outlines the diverse applications of neural networks to signal processing, time series, imaging, etc. 2. "Astronomy": Neural network applications in astronomy, such as adaptive optics and telescope guidance. 3. "Chains of Coupled Oscillators": Their connection with the lamprey central pattern generator. 4. "Chaos in Axons": An excellent review of chaos experimentally in squid axons and numerically with nerve equations. 5. "Collective Behavior of Coupled Oscillators": A study of the phase and complex Ginzburg-Landau model. 6. "Computer Modeling Methods for Neurons": Good overview of numerical modeling of neurons. 7. "Computing with Attractors": Overview of omputing and feedback networks with attractors and a fascinating discussion of the possible existence of attractors in the brain. 8. "Constrained Optimization and the Elastic Net": Useful discussion of application of neural networks to optimization problems. 9. "Data Clustering and Learning": Good discussion of parameter estimation of mixture models by parametric statistics and vector quantization of a data set by combinatorial optimization. 10. "Diffusion Models of Neuron Activity": Discusses 1-dimensional stochastic diffusion models for the neuron membrane potential. 11. "Disease: Neural Network Models": Interesting overview of neural net computational models of various mental illnesses. 12. "Dynamics and Bifurcation of Neural Networks": Discussion of neural nets and their behavior as dynamical systems. 13. "Emotion and Computational Neuroscience": Fascinating discussion of computational models of emotion. 14. "Investment Management": A discussion of tactical asset allocation neural network methods in asset management. 15. "Learning and Centralization: Theoretical Bounds": Overview of computational learning theory. 16. "Locust Flight": Interesting neural network study of the locust flight system. 17. "Neural Optimization": Discussion of combinatorial optimization using Ising and Potts neural networks. 18. "PAC Learning and Neural Networks": Overview of the Valiant "probabilistically correct learning paradigm in neural networks. 19. "Protein Structure Prediction": Neural network applications to prediction of protein secondary structure. 20. "Schema Theory": Extremely interesting overview of schemas. 21. "Speech Recognition: Pattern Matching": Excellent discussion of the applications of hidden Markov models to speech recognition. 22. "Statistical Mechanics of Neural Networks": Discussion of the use of the Hopfield model in neural networks. 23. Vapnik-Chervonenkis Dimension of Neural Networks": Very interesting discussion of the VC-dimension of neural networks. |
| |
| "An excellent reference" | 2001-06-03 |
| - Reviewed By Dr. Lee D. Carlson from Baltimore, Maryland USA |
Review of Second Edition (January 2008):
This sizable collection of articles updates the first volume with many discoveries and conceptual developments that were unknown at the time. Meant of course for reference, a typical reader, such as this reviewer, would probably not read every article in the collection but would instead concentrate on the ones of primary interest. The editor however does offer advice on "how to use this book" at the beginning of the book, for those readers who intend to use it as their primary source of information, or for instructors who will use it as a supplement to such classes as brain theory, artificial intelligence, computational neuroscience, and cognitive neuroscience. All of these topics are represented, with emphasis of course on those that the editor finds important. Time constraints will of course play in role in any sampling algorithm for the articles, but every article that was studied by this reviewer was well worth the time spent.
One of these articles, written by the editor, gave an overview of his work on the `mirror system hypothesis' (MSH). This work has been widely discussed in the literature on evolutionary linguistics since the first edition of this book, and when confronting it for the first time may seem like a radical hypothesis. Such skepticism is aggravated by the lack of any historical record for the structure of the brain, and so any theories on language evolution will remain more tentative as compared to other scientific theories. The editor though wants the reader to consider evidence for the mirror system hypothesis that is drawn from existing life forms. Thus he proposes that we examine the "mirror system" for grasping in monkeys, which he asserts contains `mirror neurons" that are activated when the monkey performs a specific hand action and when it only observes a human or other monkey performing a similar action. The MSH is the assertion that the matching in the neural code between observation and execution occurs in the common ancestor of monkey and human. Further, this matching explains the notion of language `parity', which asserts that a spoken utterance has essentially identical semantics between speaker and listener. The editor reviews his ideas on what brain mechanisms are responsible for language and grasping, and whether a mirror system is indeed present in humans. Experiments using proton emission topography support his thesis to some extent, but he cautions that the a lot more work needs to be done before one can make definitive conclusions. His thesis though is a plausible one on the surface, and interesting in that it proposes that language originally evolved not from a need for communication but from a need to recognize a set of actions. "Language readiness" then, resulted from an extension of the mirror system from being able to recognize single actions to being able to imitate compound actions. A natural question to ask here is why sophisticated grammatical constructions, some of them semantically awkward and of no practical value, would evolve from the mere need to imitate, which itself is not really complex from any reasonable measure of complexity. The editor is aware of these kinds of objections, for in the article he addresses them under the guise of `protospeech', wherein he postulates two evolutionary stages for its development. His assertions in this regard are interesting for they involve the need for cooperation between two or more areas of the brain. Along these same lines, and even more fascinating, is the editor's discussion on neuronal models for the mirror system, for when he proposes a canonical structuring for sentences he is actually asserting a kind of "entanglement" (he does not use this terminology in the article) between the F5 area and its mirror.
Review of First Edition:
This complilation of articles by leading experts in the field gives an excellent overview of studies in cognitive theory and the theory and applications of neural networks. The first two parts of the book give an overview and background of the properties of neurons and gives guidance to the reader on what sequence the articles are to be read. This reviewer did not read all of the articles, but only those that piqued his interest. such as the following articles which are particularly well-written and informative: 1. "Applications of Neural Networks": Outlines the diverse applications of neural networks to signal processing, time series, imaging, etc. 2. "Astronomy": Neural network applications in astronomy, such as adaptive optics and telescope guidance. 3. "Chains of Coupled Oscillators": Their connection with the lamprey central pattern generator. 4. "Chaos in Axons": An excellent review of chaos experimentally in squid axons and numerically with nerve equations. 5. "Collective Behavior of Coupled Oscillators": A study of the phase and complex Ginzburg-Landau model. 6. "Computer Modeling Methods for Neurons": Good overview of numerical modeling of neurons. 7. "Computing with Attractors": Overview of omputing and feedback networks with attractors and a fascinating discussion of the possible existence of attractors in the brain. 8. "Constrained Optimization and the Elastic Net": Useful discussion of application of neural networks to optimization problems. 9. "Data Clustering and Learning": Good discussion of parameter estimation of mixture models by parametric statistics and vector quantization of a data set by combinatorial optimization. 10. "Diffusion Models of Neuron Activity": Discusses 1-dimensional stochastic diffusion models for the neuron membrane potential. 11. "Disease: Neural Network Models": Interesting overview of neural net computational models of various mental illnesses. 12. "Dynamics and Bifurcation of Neural Networks": Discussion of neural nets and their behavior as dynamical systems. 13. "Emotion and Computational Neuroscience": Fascinating discussion of computational models of emotion. 14. "Investment Management": A discussion of tactical asset allocation neural network methods in asset management. 15. "Learning and Centralization: Theoretical Bounds": Overview of computational learning theory. 16. "Locust Flight": Interesting neural network study of the locust flight system. 17. "Neural Optimization": Discussion of combinatorial optimization using Ising and Potts neural networks. 18. "PAC Learning and Neural Networks": Overview of the Valiant "probabilistically correct learning paradigm in neural networks. 19. "Protein Structure Prediction": Neural network applications to prediction of protein secondary structure. 20. "Schema Theory": Extremely interesting overview of schemas. 21. "Speech Recognition: Pattern Matching": Excellent discussion of the applications of hidden Markov models to speech recognition. 22. "Statistical Mechanics of Neural Networks": Discussion of the use of the Hopfield model in neural networks. 23. Vapnik-Chervonenkis Dimension of Neural Networks": Very interesting discussion of the VC-dimension of neural networks. |
| |
International Available
