Analysis of Rachmaninoff's Piano Performances Using Inductive Logic Programming (Extended Abstract)
نویسنده
چکیده
The project outlined here is an attempt to use inductive logic programming ([6]) to determine various interpretative rules which the pianist, Sergei Rachmaninoff, may have used during his pianoforte performances. During the 1920's Rachmaninoff recorded a number of recitals on the Ampico Recording Piano ([4]). This method of capturing the performance not only recorded the notes, duration and tempo, but also the dynamics of the key pressure and pedalling, in a digital (in actual fact, binary) form, which easily lends itself to conversion into a computer readable form. To complement this performance information, it was also necessary to represent the musical structure of the piece being performed, so that a general analysis could be performed, rather than one specific to that particular piece. For simplicity, only the melodies of the pieces involved were subjected to analysis, although better results may be obtained from a full analysis of the accompanying harmonic and contrapuntal structures. The two sets of information, structural analysis and performance analysis were encoded into PROGOL scripts ([5]), which were used to attempt to determine general rules (in the form of universal predicates) underlying the data set. Two pieces were analysed in this manner: Rachmaninoff’s Prelude in C sharp minor, opus 3 number 2 (Ampico roll number 57504) and Mendelssohn’s Song without Words Opus 67 number 4 (Ampico Roll number 59661).
منابع مشابه
Incorporating a folding rule into inductive logic programming
Many inductive logic programming systems have operators reorganizing the program so far inferred, such as the intra-construction operator of CIGOL. At the same time, there is a similar reorganizing operator, called the “folding rule,” developed in program transformation. We argue that there are advantages in using an extended folding rule as a reorganizing operator for inductive-inference syste...
متن کاملScalable acceleration of inductive logic programs
Inductive logic programming systems are recognised as an emerging but powerful paradigm for machine learning which can make use of background knowledge to produce theories expressed in logic. They have been applied successfully to a wide range of problem domains, from protein structure prediction to satellite fault diagnosis. However, their execution can be computationally demanding. We introdu...
متن کاملA laboratory investigation on the potential of computational intelligence approaches to estimate the discharge coefficient of piano key weir
The piano key weir (PKW) is a type of nonlinear control structure that can be used to increase unit discharge over linear overflow weir geometries, particularly when the weir footprint area is restricted To predict the outflow passing over a piano key weir, the discharge coefficient in the general equation of weir needs to be known. This paper presents the results of laboratory model testing of...
متن کاملAutomatically Exploring Hypotheses About Fault Prediction: A Comparative Study of Inductive Logic Programming Methods
We evaluate a class of learning algorithms known as inductive logic programming (ILP) methods on the task of predicting fault occurrence in C++ classes. Using these methods, a large space of possible hypotheses is searched in an automated fashion; further, the hypotheses are based directly on an abstract logical representation of the software, rather than on manually proposed numerical metrics ...
متن کاملA differentiable approach to inductive logic programming
Recent work in neural abstract machines has proposed many useful techniques to learn sequences of applications of discrete but differentiable operators. These techniques allow us to model traditionally procedural problems using neural networks. In this work, we are interested in using neural networks to learn to perform logic reasoning. We propose a model that has access to differentiable opera...
متن کامل