Abstract
Artificial neural networks (ANN) enable problem solving by changing the structure of interconnected components. In analogy to the biological model, these interconnected elements are referred to as neurons and make up the basic units of information processing. A simple model of a biological neuron is composed of the following components, illustrated in figure 9.1: A large number of short nerve fibers called dendrites conduct impulses from the adjacent neurons to the cell body. The cell reacts to this input with an impulse that is carried to other cells by an axon. An axon is a long nerve fiber that may be up to one meter in length and undergoes extensive branching at its end which enables communication with dendrites or other cell bodies. The neurons are connected via synapses. When an electrical impulse runs through an axon, this causes the synapse to release a substance called a neurotransmitter which is picked up by a neighboring dendrite and changes the electric potential of the cell. When a particular threshold value is reached, an action potential is generated in a cell that in turn is sent along the axon through the synapses to the dendrites of the connected neurons. The human brain has approximately 1011 interconnected neurons whose reaction time is estimated at one millisecond. The average processing time for the recognition of complex visual and/or acoustic information by a human brain is approximately 0.1 seconds. If biological neuronal systems would work like strictly sequential digital computers, only 100 instructions would be possible in that time frame [12, p. 172].
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bellgrad MI, Tsang CP (1994) Harmonizing music the Boltzmann way. Connection Science, 6, 1994
Dannenberg RB, Thom B, Watson D (1997) A machine learning approach to musical style recognition. In: Proceedings of the 1997 International Computer Music Conference. International Computer Music Association, San Francisco
Hebb DO (1949) The organization of behavior. Wiley, New York
Hild H, Feulner J, Menzel W (1992) HARMONET: A neural net for harmonizing chorales in the style of J.S. Bach: Advances in Neural Information Processing Systems 4
Hochreiter S, Schmidhuber, J (1997) Long Short-Term Memory. Neural Computation, 9/8, 1997
Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the United States of America, 79, 1982
Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences of the United States of America, 81, 1984
Kiernan F (2000) Score-based style recognition using artificial neural networks. In: Proceedings of the first International Conference on Music Information Retrieval (ISMIR 2000). Plymouth, Mass
Kohonen T (1972) Correlation Matrix Memories. IEEE Transactions on Computers C-21, 4, April 1972
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43, 1982
Laden B, Keefe DH (1989) The representation of pitch in a neural net model of chord classification. Computer Music Journal 13/4, 1989
Lämmel U, Cleve J (2001) Lehr-und Übungsbuch Künstliche Intelligenz. Fachbuchverlag Leipzig im Carl-Hanser-Verlag, München. ISBN 3-446-21421-6
Luger GF, Stubblefield W (1998) Artificial intelligence. Structures and strategies for complex problem solving, 3rd edn. Addison-Wesley Longman, Amsterdam. ISBN 0-805-31196-3
McCulloch W, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5, 1943
McCulloch W (1945) A heterarchy of values determined by the topology of nervous nets. Bulletin of Mathematical Biophysics, 5, 1945
Minsky M, Papert S (1969) Perceptrons: An introduction to computational geometry. MIT Press, Cambridge, Mass
Miranda ER, Biles JA (eds) (2007) Evolutionary computer music. Springer, London. ISBN 978-1-84628-599-8
Mozer MC (1994) Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multiscale processing. Connection Science, 1994
Pazos A, del Riego SA, Dorado J, Romero-Cardalda JJ (1999) Connectionist system for music interpretation. In: International Joint Conference on Neural Networks (IJCNN’99), vol 6. IEEEE, New York, pp 4002–4005
Rosenblatt F (1962) Principles of neurodynamics. Spartan, New York
Rumelhart DE, Hinton GE, Williams R (1986) Learning internal representations by error propagation. In: Rumelhart D, McClelland JL (eds) (1986) Parallel distributed processing: Explorations in the microstructure of cognition, 1: Foundations. MIT Press, Cambridge, Mass
Rumelhart DE, Hinton GE, Williams R (1986) Learning internal representations by back-propagating errors. Nature, 323, 1986
Schmidhuber J, Eck D (2002) A first look at music composition using LSTM recurrent neural networks. Technical Report IDSIA-07-02, 2002
Schmidhuber J, Eck D (2005) Composing music with LSTM recurrent networks — Blues improvisation. http://www.idsia.ch/ juergen/blues/index.html Cited 3 Nov 2005
Shepard RN (1982) Geometrical approximations to the structure of musical pitch. Psychological Review, 89/4, 1982
Tillmann B (1999) Connectionist simulation of tonal knowledge representation. Publications Journées d’Informatique Musicale, Issy-Les-Moulineaux, 1999
Tillmann B, Bharucha JJ, Bigand E (2000) Implicit learning of tonality: A self-organizing approach. Psychological Review, 107/4, 2000
Todd PM (1989) A connectionist approach to algorithmic composition. Computer Music Journal, 13/4, 1989
Werbos P (1974) Beyond regression: New tools for prediction and analysis in the behavioral sciences. PhD Thesis, Harvard University, 1974
Widrow B, Hoff ME (1960) Adaptive switching circuits. IRE Western Electric Show and Convention Record, 4, August 23, 1960
Rights and permissions
Copyright information
© 2009 Springer-Verlag/Wien
About this chapter
Cite this chapter
(2009). Artificial Neural Networks. In: Algorithmic Composition. Springer, Vienna. https://doi.org/10.1007/978-3-211-75540-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-211-75540-2_9
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-75539-6
Online ISBN: 978-3-211-75540-2
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)