Musical Networks : Parallel Distributed Perception and Performance

, by Niall Griffith and Peter M. Todd (Eds.)

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

ISBN: 9780262071819 | 0262071819
Cover: Hardcover
Copyright: 3/5/1999

Rent

(Recommended)

$8.27

Term

Due

Price

Semester

Dec 13

$9.19

Quarter

Sep 1

$8.72

Short Term

Jul 26

$8.27

*This item is part of an exclusive publisher rental program and requires an additional convenience fee. This fee will be reflected in the shopping cart.
Buy Used

Usually Ships in 2-4 Business Days

$9.37
Buy New

Special Order: 1-2 Weeks

$12.56

This volume presents the most up-to-date collection of neural network models of music and creativity gathered together in one place. Chapters by leaders in the field cover new connectionist models of pitch perception, tonality, musical streaming, sequential and hierarchical melodic structure, composition, harmonization, rhythmic analysis, sound generation, and creative evolution. The collection combines journal papers on connectionist modeling, cognitive science, and music perception with new papers solicited for this volume. It also contains an extensive bibliographyof related work. Contributors: Shumeet Baluja, M. I. Bellgard, Michael A. Casey, Garrison W. Cottrell, Peter Desain, Robert O. Gjerdingen, Mike Greenhough, Niall Griffith, Stephen Grossberg, Henkjan Honing, Todd Jochem, Bruce F. Katz, John F. Kolen, Edward W. Large, Michael C. Mozer, Michael P. A. Page, Caroline Palmer, Jordan B. Pollack, Dean Pomerleau, Stephen W. Smoliar, Ian Taylor, Peter M. Todd, C. P. Tsang, Gregory M. Werner.

Preface
Pitch And Tonality
Modelling Pitch Perception with Adaptive Resonance Theory Artificial Neural Networks
Introduction
Aspects of Musical Pitch
Pattern-recognition Theories
Implementations of Pattern-recognition Theories
The Use of ANNs for Pitch Classification
Outline for an Adaptive Resonance Theory System
Sampling and Spectrum Analysis
Mapping from the Fourier Spectrum to a 'Semitone Bin' Representation
The ART Architecture and Its Use in Pitch Classification
ART1
ART2
Why supervised learning is needed
ARTMAP
Pitch Classification Experiments Using ARTMAP
Training the ARTMAP System
The Test Data
Results
Conclusions
Recent and Future Work
References
Development of Tonal Centres and
Abstract Pitch as Categorizations of Pitch Use
Introduction
Computational Models of Key and Tonality
Pitch Use and the Development of Tonality
Inducing Key from Patterns of Pitch Use
Abstracting Pitch from Patterns of Interval Use
The Intervals of the Major Scale
An Outline Model of Pitch
Abstraction
Topological Maps of Pitch-interval Use
Integrating Patterns of Interval over Pitch and Key
Mapping Key and Pitch and Interval Memories to Degree
Conclusions
Acknowledgements
Notes
References
Understanding Musical Sound with Forward Models and Physical Models
Introduction
Direct Inverse Modeling
Direct Inverse Modeling of a Convex Solution Space
Direct Inverse Modeling of a Non-convex Solution Space
Forward Models for Non-convex Data
Training the Forward Model
Training the Inverse Model Using the Forward Model
Performance on Novel Data
Conclusions
Acknowledgements
References
Rhythm And Meter
Resonance and the Perception of Musical Meter
Introduction
Connectionist Approaches to Musical Expectancy
Rhythm and Meter
Music-theoretic Perspective
Psychological Perspective
Connectionist Perspective
Mathematical Considerations
An Entrainment Model
The Basic Oscillatory Unit
Response of Single Units to Periodic Stimulation
Rhythmic Stimulation
Implementation Issues
General Discussion
Future Work
Implications for Connectionist Approaches to Expectancy
Conclusions
Acknowledgements
Notes
References
Modelling Musical Perception: A Critical View
Introduction
Reviewing the Models
The Analysis of Musical Rhythm
The quantization problem
A connectionist approach
Comparing the symbolic and connectionist solutions
Interpreting the results
Expressive Performance
Conclusions
Notes
References
A Reply to S. W. Smoliar's 'Modelling Musical Perception: A Critical View'
Notes
References
Melodic Memory, Structure, And Completion
Pitch-based Streaming in Auditory Perception
Auditory Streaming, Pitch Perception, and Music Perception
Phonemic Restoration, Attentive Matching, and Adaptive Resonance
Pitch Cues for Streaming
A Neural Model of Pitch Perception and Auditory Streaming
The SPINET Model
ART Matching and Resonance in ARTSTREAM
Resonant Dynamics During Auditory Streaming
Simulation of the Auditory Continuity Illusion
Apparent Motion in Music?
Acknowledgements
References
Appendix
Outer and Middle Ear
Cochlear Filterbank
Energy Measure
Spectral Stream Layer
Pitch Summation Layer
Pitch Stream Layer
Apparent Motion in Music?
Introduction
The Basic Grossberg-Rudd Model
Level 1: Input
Level 2: Temporal Reintegration
Level 3: Spatial Reintegration
Level 4: Motion Analysis
Tracking Individual Voices in a Polyphonic Texture
Tracking Linear Processes: Scales and Arpeggios
Multiplex Interpretations of an Ambiguous Melodic Figure
The van Noorden Demonstration: Pitch Streaming
Trills
Emergent Broader Streams: Parallel Voices and Outer-voice Salience
Discussion
References
Modelling the Perception of Musical Sequences with Self-organizing Neural Networks
Introduction
Previous Connectionist Models
Unsupervised Classification and the Masking Field
The SONNET 1 Network
Formal Description
Simulations
The Generation of Expectations
Network Hierarchies and Hierarchical Expectations
Recognition and Recall
Summary
Notes
Acknowledgements
References
An Ear for Melody
Introduction
Affect and the Activation
The Model
Note Recognition
Group Recognition Model
Melodic grouping
Representation
Categorization
Simulation Results
Complexity and Affect
Familiarity and Affect
The Effect of Exposure to a Musical Genre
Degradation of Good Melodies
Discussion
Acknowledgement
Notes
References
Composition
Neural Network Music Composition by Prediction: Exploring the Benefits of Psychoacoustic Constraints and Multi-scale Processing
Introduction
Transition Table Approaches to Algorithmic Music Composition
Note-by-note Composition
The Concert Architecture
Unit Activation Rules
Training Procedure
Representing Musical Elements
Pitch Representation
Duration Representation
Chord Representation
Basic Simulation Results
Extending a C-major Diatonic Scale
Learning the Structure of Diawnic Scales
Learning Random Walk Sequences
Learning Interspersed Random Walk Sequences
Learning AABA Phrase Patterns
Discussion
Capturing Higher-order Musical Organization
AABA Phrase Patterns Revisited
Larger Simulation Experiments
Composing Melodies in the Style of Bach
Composing Melodies in the Style of European Folk Tunes
Explicit Training on Higher-order Structure: The Waltz Experiment
Discussion
Acknowledgements
Notes
References
Harmonizing Music the Boltzmann Way
Introduction
Background
Chorale Harmonization
AI/Music Research and Chorale Harmonization
Neural network approaches
Motivations for Current Work
Completion, chorale harmonization and constraint satisfaction
Learning to harmonize using an effective Boltzmann machine
The Effective Boltzmann Machine
Music Representation
Error control codes and the pitch-height representation
Learning the Local Contexts in Chorales
Completion of an Arbitrary-length Melody
Experimentation
Completion of a Chorale in Training Set
Completion of Chorale Melody that Is Not in the Training Set
Effects of absolute constraints
Start/end phrase units
Effects of a Different Window Size
Using the Energy Gap to Determine the Validity of the Harmony Produced by EBM
Conclusion
Acknowledgements
References
Reduced Memory Representations for Music
Introduction
Theories of Memory for Music
A Reductionist Mechanism
Empirical Investigation
Method
Subjects
Materials
Apparatus
Procedure
Results
Coding improvisations
Comparison with theoretical predictions
Discussion
Network Model
Network Implementation
Method
Training the network
Testing the network
Results
Tests of well-formedness
Test of representational structure
Discussion
General Discussion
Musical Improvisation and Reduced Memory Structures
Temporal Structure and Constituent Structure
Comparison with Other Connectionist Models
Limitations and Future Work
Conclusions
Acknowledgements
Notes
References
Appendix: Network Training Set
Frankensteinian Methods for Evolutionary Music Composition
Introduction: Following in Frankenstein's Footsteps
"My workshop of filthy creation": Designing and Training Composition Systems
"A new species": Evolving Composition Systems
Humans as Critics
Rule-based Critics
Learning-based Critics
"My creator... your master": Coevolving Music Creators and Critics
Coevolving Rhythm-generating and Judging Neural Networks
Coevolving Hopeful Singers and Music Critics
Resulting Song Change over Time
Resulting Song Diversity within Populations
''The instrument of future mischief": Conclusions, Implications, and Further Work
Acknowledgements
References
Towards Automated Artificial Evolution for Computer-generated Images
Introduction
Image Evolution
Background Information
Simulating Evolution with Genetic Algorithms
An Introduction to Genetic Algorithms
The Composition of Chromosomes
Recombination of Chromosomes
Assessing the Fitness of a Chromosome
The Need for Preserving Diversity in Genetic Search
Mutation
Interactively Evolving Computer-generated Images
The User Interface
Using the image repository
Selected Images
Towards Automation
Motivation and Overview
The Training Set
Preliminary Trials and Improvements
Gauging Network Performance
Using a Smaller Architecture: Small ANN 1
A Comparison of Architectures
Discussion and Pictorial Results
Conclusions and Future Directions
Acknowledgements
References
Appendix: Typical Image Equations
The Connectionist Air Guitar: A Dream Come True
Notes
Bibliography
Contributors
Table of Contents provided by Publisher. All Rights Reserved.

Please wait while the item is added to your bag...

FREE SHIPPING

Amazon no longer offers textbook rentals. We do!

Musical Networks : Parallel Distributed Perception and Performance

Summary

Table of Contents

Supplemental Materials