Book contents
- Frontmatter
- Contents
- Contributors
- Introduction: Modelling perception with artificial neural networks
- Part I General themes
- 1 Neural networks for perceptual processing: from simulation tools to theories
- 2 Sensory ecology and perceptual allocation: new prospects for neural networks
- Part II The use of artificial neural networks to elucidate the nature of perceptual processes in animals
- Part III Artificial neural networks as models of perceptual processing in ecology and evolutionary biology
- Part IV Methodological issues in the use of simple feedforward networks
- Index
- References
1 - Neural networks for perceptual processing: from simulation tools to theories
from Part I - General themes
Published online by Cambridge University Press: 05 July 2011
By
Book contents
- Frontmatter
- Contents
- Contributors
- Introduction: Modelling perception with artificial neural networks
- Part I General themes
- 1 Neural networks for perceptual processing: from simulation tools to theories
- 2 Sensory ecology and perceptual allocation: new prospects for neural networks
- Part II The use of artificial neural networks to elucidate the nature of perceptual processes in animals
- Part III Artificial neural networks as models of perceptual processing in ecology and evolutionary biology
- Part IV Methodological issues in the use of simple feedforward networks
- Index
- References
Summary
Introduction
This paper has two main aims. First, to give an introduction to some of the construction techniques – the ‘nuts-and-bolts’ as it were – of neural networks deployed by the authors in this book. Our intention is to emphasise conceptual principles and their associated terminology, and to do this wherever possible without recourse to detailed mathematical descriptions. However, the term ‘neural network’ has taken on a multitude of meanings over the last couple of decades, depending on its methodological and scientific context. A second aim, therefore, given that the application of the techniques described in this book may appear rather diverse, is to supply some meta-theoretical landmarks to help understand the significance of the ensuing results.
In general terms, neural networks are tools for building models of systems that are characterised by data sets which are often (but not always) derived by sampling a system input-output behaviour. While a neural network model is of some utility if it mimics the behaviour of the target system, it is far more useful if key mechanisms underlying the model functionality can be unearthed, and identified with those of the underlying system. That is, the modeller can ‘break into’ the model, viewed initially as an input-output ‘black box’, and find internal representations, variable relationships, and structures which may correspond with the underlying target system. This target system may be entirely non-biological (e.g. stock market prices), or be of biological origin, but have nothing to do with brains (e.g. ecologically driven patterns of population dynamics).
- Type
- Chapter
- Information
- Modelling Perception with Artificial Neural Networks , pp. 7 - 34Publisher: Cambridge University PressPrint publication year: 2010
References
& 1982. Phenomenal coherence of moving visual patterns. Nature 300, 523–525.CrossRefGoogle ScholarPubMed
, & 1985. Encoding of spatial location by posterior parietal neurons. Science 230, 456–458.CrossRefGoogle ScholarPubMed
1985. Learning by statistical cooperation of sele-interested neuron-like computing elements. Hum Neurobiol 4, 229–256.Google ScholarPubMed
& 1985. Pattern-recognizing stochastic learning automata. IEEE Syst Man CyberneticsSMC-15, 360–375.CrossRefGoogle Scholar
, & 1983. Neuronlike elements that can solve difficult learning control problems. IEEE Trans Systems Man Cybernetics 13, 835–846.Google Scholar
& 1994. Neural networks: a review from a statistical perspective. Statist Sci 9, 2–54.CrossRefGoogle Scholar
, & 1990. On the control of automatic processes – a parallel distributed-processing account of the Stroop effect. Psychol Rev 97, 332–361.CrossRefGoogle ScholarPubMed
2002. Levels of analysis in neural modeling. In Encyclopedia of Cognitive Science (ed. L. Nadel). Nature Publishing Group; John Wiley & Sons Ltd.Google Scholar
& 1999. Computational analyses in cognitive neuroscience: in defense of biological implausibility. Psychon Bull Rev 6, 173–182.CrossRefGoogle ScholarPubMed
, & 1997. Propagation of activity-dependent synaptic depression in simple neural networks. Nature 388, 439–448.CrossRefGoogle ScholarPubMed
2001. Scientific models, connectionist networks, and cognitive science. Theory Psychol 11, 97–117.CrossRefGoogle Scholar
1997. An Introduction to Neural Networks. UCL Press (Taylor and Francis group).CrossRefGoogle Scholar
, , & 2004. Computational models of the basal ganglia: from robots to membranes. Trends Neurosci 27, 453–459.CrossRefGoogle ScholarPubMed
& 1992. A self-organising neural network model of image velocity encoding. Biol Cybernetics 68, 173–181.CrossRefGoogle ScholarPubMed
& 1991. Lesioning an attractor network – investigations of acquired dyslexia. Psychol Rev 98, 74–95.CrossRefGoogle ScholarPubMed
& 1952. A quantitative description of membrane current and its application to conduction and excitation in nerve. J Physiol 117, 500–544.CrossRefGoogle ScholarPubMed
1982. Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA 79, 2554–2558.CrossRefGoogle ScholarPubMed
& 1968. Receptive fields and functional architecture of monkey striate cortex. J Physiol 195, 215–243.CrossRefGoogle ScholarPubMed
, & 1991. Task decomposition through competition in a modular connectionist architecture. Cogn Sci 15, 219–250.CrossRefGoogle Scholar
1986. Serial Order: a Parallel Distributed Approach. University of California, Institute for Cognitive Science.
1999. The Biophysics of Computation: Information Processing in Single Neurons. Oxford University Press.Google Scholar
, & 2002. Single-cell models. In The Handbook of Brain Theory and Neural Networks (ed. ). MIT Press.Google Scholar
1987. An introduction to computing with neural nets. ASSP Magazine, IEEE 4, 4–22.CrossRefGoogle Scholar
1991. Half a century of research on the Stroop effect – an integrative review. Psychol Bull 109, 163–203.CrossRefGoogle ScholarPubMed
, & 1989. Formation of disconnected decision regions with a single hidden layer. In International Joint Conference on Neural Networks, Vol. 1, pp. 455–460.
1982. Vision: A Computational Investigation into Human Representation and Processing of Visual Information. W.H. Freeeman and Co.Google Scholar
& 1976. From Understanding Computation to Understanding Neural Circuitry. MIT AI Laboratory.
, & 1995. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychol Rev 102, 419–457.CrossRefGoogle ScholarPubMed
& 1985. Distributed memory and the representation of general and specific information. J Exp Psychol Gen 114, 159–188.CrossRefGoogle ScholarPubMed
1991. Networks and theories – the place of connectionism in cognitive science. Psychol Sci 2, 387–395.CrossRefGoogle Scholar
& 1943. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophysics 7, 115–133.CrossRefGoogle Scholar
, , & 1985. The analysis of moving visual patterns. In Pattern Recognition Mechanisms (ed. , & ), pp. 117–151. Springer-Verlag.Google Scholar
1982. Learning-logic. Office of Technology Licensing, Stanford University.
1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65, 386–408.CrossRefGoogle Scholar
& 1995. Improving neural net generalisation. In Proceedings of IGARSS'95. Firenze, Italy.Google Scholar
, & . 1986. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press.Google Scholar
& 1993. Learning and connectionist representations. In Attention and Performance XIV (ed. & ), pp. 3–31. MIT Press.Google Scholar
& 1996. Global optimization for neural network training. IEEE Computer 29, 45–54.CrossRefGoogle Scholar
& 1998. Introduction to synaptic circuits. In The Synaptic Organization of the Brain (ed. G. M. Shepherd), pp. 1–36. Oxford University Press.Google Scholar
1974. Cross-validatory choice and assesment of statistical predictions. J R Statist Soc B36, 111–133.Google Scholar
1935. Studies of interference in serial verbal reactions. J Exp Psychol 18, 643–662.CrossRefGoogle Scholar
1988. Learning to predict by the method of temporal differences. Machine Learn 3, 9–44.CrossRefGoogle Scholar
1980. A model for the formation of ocular dominance stripes. Proc R Soc B 208, 243–264.CrossRefGoogle ScholarPubMed
1995. Connectionist and symbolic representations. In The Handbook of Brain Theory and Neural Networks, 1st Edn. (ed. ), pp. 243–247. MIT Press.Google Scholar
1996. Backpropagator's review. www.dontveter.com/bpr/activate.html
& 1991. Occlusion and the perception of coherent motion. Vision Res 31, 1967–1978.CrossRefGoogle ScholarPubMed
1973. Self-organization of orientation sensitive cells in the striate cortex. Kybernetik 14, 85–100.CrossRefGoogle Scholar
1976. On perceived identity 1: The direction of motion of straight lines. In On Perception (ed. ). Quadrangle.Google Scholar
1974. Beyond Regression: New Tools for Prediction and Analysis in the Behavioural Sciences. Harvard University.Google Scholar
& 1960. Adaptive switching circuits. In IRE WESCON Convention Record, pp. 96–104.
& 1987. Geometric analysis of neural network capabilities. In 1st IEEE International Conference on Neural Networks, Vol. III, pp. 385–392. San Diego, California.Google Scholar
& 1976. How patterned neural connections can be set up by self-organization. Proc R Soc B 194, 431–445.CrossRefGoogle ScholarPubMed
& 1988. A back-propagation programmed network that simulates response properties of a subset of posterior parietal neurons. Nature 331, 679–684.CrossRefGoogle ScholarPubMed