A Connectionist Approach To Algorithmic Composition

  title={A Connectionist Approach To Algorithmic Composition},
  author={Peter M. Todd and Gareth Loy},
  journal={Computer Music Journal},
  • P. Todd, G. Loy
  • Published 24 January 1989
  • Computer Science
  • Computer Music Journal
With the advent of von Neumann-style computers, widespread exploration of new methods of music composition became possible. For the first time, complex sequences of carefully specified symbolic operations could be performed in a rapid fashion. Composers could develop algorithms embodying the compositional rules they were interested in and then use a computer to carry out these algorithms. In this way, composers could soon tell whether the results of their rules held artistic merit. This… 

Figures and Topics from this paper

An Application of Evolutionary Algorithms to Music: - Co-Evolving Melodies and Harmonization
Algorithmic composition is a field that is close to 60 years old, and has seen much research. Systems today are able to do a wide range of compositional tasks, ranging from simple melody generation
Frankensteinian methods for evolutionary music composition
A new method that uses coevolution to create linked artificial music critics and music composers is presented, and it is described how this method can attach the separate parts of rules, learning, and evolution together into one coherent body.
NetNeg: A Hybrid Interactive Architecture for Composing Polyphonic Music in Real Time
This research focuses on the question whether there is any advantage in integrating a neural network together with a distributed artiicial intelligence approach in the musical domain and presents a new approach for composing and analyzing polyphonic music.
Connectionist Music Composition Based on Melodic, Stylistic, and Psychophysical Constraints [Technical report CU–CS–495–90]
Algorithmic music composition involves the use of rules to generate melodies. One simple but interesting technique is to select notes sequentially according to a transition table that specifies the
Neural network music composition and the induction of multiscale temporal structure
  • M. Mozer
  • Computer Science
    Wissensbasierte Systeme
  • 1991
An improved algorithm is described that is better able to induce temporal structure at multiple scales and trained on a set of melodies written in a certain style and then is able to compose new melodies in the same style.
NetNeg: A connectionist-agent integrated system for representing musical knowledge
The system presented here shows the feasibility of modeling the knowledge involved in a complex musical activity by integrating sub-symbolic and symbolic processes and enables the musician to encode his knowledge, intuitions, and aesthetic taste into different modules.
1 Overview "If a complex structure is completely unredundant-if no aspect of its structure can be inferred from any other-then it is its own simplest description. We can exhibit it but we cannot
AI Methods in Algorithmic Composition: A Comprehensive Survey
This survey aims to be a comprehensive account of research on algorithmic composition, presenting a thorough view of the field for researchers in Artificial Intelligence.
Traditional patterns and textures as values for meaningful automatization in music
This contribution focuses on the accelerated loss of traditional sound patterning in music, parallel to the loss of linguistic and cultural variety in a world increasingly globalised by market
NetNeg : A Hybrid System Architecture for Composing
There are musical activities in which we are faced with symbolic and sub-symbolic processes. This research focuses on the question whether integrating a neural network together with a distributed


An Expert System for Computer-Assisted Composition
EMI was begun as an analysis tool for generating extensive lists of motivic patterns, it quickly grew into an imitative projector of possible next intervals of given phrases, which included projections of linguistic parselike networks for phrase structures, intensely rigorous motive replications, and a proclivity for analyzing music by intervals rather than by pitch.
Compositional Applications of Stochastic Processes
Although a composer has a different objective, mathematical techniques developed for analysis can be of great practical use in the formal, structured environment of computer music systems.
Machine tongues XII : Neural networks
The continuing evolution of high-level languages can be seen as an ongoing attempt to transfer this undesirable complexity from the domain of the programmer to that of the computer itself, through constraint languages such as TK!Solver.
Finding Structure in Time
A proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory and suggests a method for representing lexical categories and the type/token distinction is developed.
Modeling the Perception of Tonal Structure with Neural Nets
The notion that individual neurons specialize to respond to complex auditory patterns has some preliminary empirical support from single-cell recording studies on animals (Weinberger and McKenna 1988).
Phoneme recognition using time-delay neural networks
The authors present a time-delay neural network (TDNN) approach to phoneme recognition which is characterized by two important properties: (1) using a three-layer arrangement of simple computing
" Machine Tongues XII : Introduction to Neural Nets
  • 1989