Modular non-computational-connectionist-hybrid neural network approach to robotic systems

Spiking neural networks are usually limited in their applications due to their complex mathematical models and the lack of intuitive learning algorithms. In this paper, a simpler, novel neural network derived from a leaky integrate and fire neuron model, the ‘cavalcade’ neuron, is presented. A simulation for the neural network has been developed and two basic learning algorithms implemented within the environment. These algorithms successfully learn some basic temporal and instantaneous problems. Inspiration for neural network structures from these experiments are then taken and applied to process sensor information so as to successfully control a mobile robot.

Instructions for an Audio Performance/Scissors Music

‘Instructions for an Audio Performance/Scissors Recording’ is a score for a performance using an amplified scissors that can be downloaded and interpreted by a performer anywhere in the world. The file functions as a manual for the performer with guidance for creating the instrument and preparing the performance space while it also provides a template for the actual sonic pattern to be followed in the live performance. Created originally for ‘Storageroom’ an online platform featuring complete exhibitions that are available for download, the piece was exhibited and interpreted in a live performance by Ayelet Lerman for the File Transfer Protocol, the contemporary section of the Haifa-Jerusalem-Tel Aviv exhibition at the Museum of Art, Haifa, Israel.

The music instinct: the evolutionary basis of musicality

Why does music pervade our lives and those of all known human beings living today and in the recent past? Why do we feel compelled to engage in musical activity, or at least simply enjoy listening to music even if we choose not to actively participate? I argue that this is because musicality—communication using variations in pitch, rhythm, dynamics and timbre, by a combination of the voice, body (as in dance), and material culture—was essential to the lives of our pre-linguistic hominin ancestors. As a consequence we have inherited a desire to engage with music, even if this has no adaptive benefit for us today as a species whose communication system is dominated by spoken language. In this article I provide a summary of the arguments to support this view.

Whether weather affects music

The creative output of composers, writers, and artists is often influenced by their surroundings. To give a literary example, it has been claimed recently that some of the characters in Oliver Twist and A Christmas Carol were based on real-life people who lived near Charles Dickens in London [Richardson, 2012]. Of course, an important part of what we see and hear is not only the people with whom we interact but also our geophysical surroundings. Of all the geophysical phenomena to influence us, the weather is arguably the most significant because we are exposed to it directly and daily. The weather was a great source of inspiration for artists Claude Monet, John Constable, and William Turner, who are known for their scientifically accurate paintings of the skies [e.g., Baker and Thornes, 2006].

Enterprise pedagogy in music: an exploration of multiple pedagogies

This article investigates the nature of enterprise pedagogy in music. It presents the results of a research project that applied the practices of enterprise learning developed in the post-compulsory music curriculum in England to the teaching of the National Curriculum for music for 11-to-14-year-olds. In doing so, the article explores the nature of enterprise learning and the nature of pedagogy, in order to consider whether enterprise pedagogy offers an effective way to teach the National Curriculum. Enterprise pedagogy was found to have a positive effect on the motivation of students and on the potential to match learning to the needs of students of different abilities. Crucially, it was found that, to be effective, not only did the teacher’s practice need to be congruent with the beliefs and theories on which it rests, but that the students also needed to share in these underlying assumptions through their learning. The study has implications for the way in which teachers work multiple pedagogies in the process of developing their pedagogical identity.

Beyond a constructivist curriculum : a critique of competing paradigms in music education

The distinction between learning to perform on an instrument or voice and learning music in a wider sense is one that is made in many countries, and is especially pertinent in England in the context of recent policy developments. This article argues that, whilst this distinction has come to represent curricula based on the opposing paradigms of behaviourist and constructivist approaches to learning, this opposition does not necessarily extend to the pedagogy through which the curricula are taught. A case study of the National Curriculum in England highlights the characteristics of a curriculum based on constructivist principles, along with the impact this has when taught in a behaviourist way. It is argued that conceiving the curriculum in terms of musical competencies and pedagogy in terms of musical understanding would provide a basis for greater continuity and higher quality in the music education experienced by young people.

PMCRI: a parallel modular classification rule induction framework

In a world where massive amounts of data are recorded on a large scale we need data mining technologies to gain knowledge from the data in a reasonable time. The Top Down Induction of Decision Trees (TDIDT) algorithm is a very widely used technology to predict the classification of newly recorded data. However alternative technologies have been derived that often produce better rules but do not scale well on large datasets. Such an alternative to TDIDT is the PrismTCS algorithm. PrismTCS performs particularly well on noisy data but does not scale well on large datasets. In this paper we introduce Prism and investigate its scaling behaviour. We describe how we improved the scalability of the serial version of Prism and investigate its limitations. We then describe our work to overcome these limitations by developing a framework to parallelise algorithms of the Prism family and similar algorithms. We also present the scale up results of a first prototype implementation.

Parallel induction of modular classification rules

The Distributed Rule Induction (DRI) project at the University of Portsmouth is concerned with distributed data mining algorithms for automatically generating rules of all kinds. In this paper we present a system architecture and its implementation for inducing modular classification rules in parallel in a local area network using a distributed blackboard system. We present initial results of a prototype implementation based on the Prism algorithm.

Towards a computationally efficient approach to modular classification rule induction

Induction of classification rules is one of the most important technologies in data mining. Most of the work in this field has concentrated on the Top Down Induction of Decision Trees (TDIDT) approach. However, alternative approaches have been developed such as the Prism algorithm for inducing modular rules. Prism often produces qualitatively better rules than TDIDT but suffers from higher computational requirements. We investigate approaches that have been developed to minimize the computational requirements of TDIDT, in order to find analogous approaches that could reduce the computational requirements of Prism.

J-PMCRI: a methodology for inducing pre-pruned modular classification rules

Inducing rules from very large datasets is one of the most challenging areas in data mining. Several approaches exist to scaling up classification rule induction to large datasets, namely data reduction and the parallelisation of classification rule induction algorithms. In the area of parallelisation of classification rule induction algorithms most of the work has been concentrated on the Top Down Induction of Decision Trees (TDIDT), also known as the ‘divide and conquer’ approach. However powerful alternative algorithms exist that induce modular rules. Most of these alternative algorithms follow the ‘separate and conquer’ approach of inducing rules, but very little work has been done to make the ‘separate and conquer’ approach scale better on large training data. This paper examines the potential of the recently developed blackboard based J-PMCRI methodology for parallelising modular classification rule induction algorithms that follow the ‘separate and conquer’ approach. A concrete implementation of the methodology is evaluated empirically on very large datasets.

Induction of modular classification rules: using Jmax-pruning

The Prism family of algorithms induces modular classification rules which, in contrast to decision tree induction algorithms, do not necessarily fit together into a decision tree structure. Classifiers induced by Prism algorithms achieve a comparable accuracy compared with decision trees and in some cases even outperform decision trees. Both kinds of algorithms tend to overfit on large and noisy datasets and this has led to the development of pruning methods. Pruning methods use various metrics to truncate decision trees or to eliminate whole rules or single rule terms from a Prism rule set. For decision trees many pre-pruning and postpruning methods exist, however for Prism algorithms only one pre-pruning method has been developed, J-pruning. Recent work with Prism algorithms examined J-pruning in the context of very large datasets and found that the current method does not use its full potential. This paper revisits the J-pruning method for the Prism family of algorithms and develops a new pruning method Jmax-pruning, discusses it in theoretical terms and evaluates it empirically.

Jmax-pruning: a facility for the information theoretic pruning of modular classification rules

The Prism family of algorithms induces modular classification rules in contrast to the Top Down Induction of Decision Trees (TDIDT) approach which induces classification rules in the intermediate form of a tree structure. Both approaches achieve a comparable classification accuracy. However in some cases Prism outperforms TDIDT. For both approaches pre-pruning facilities have been developed in order to prevent the induced classifiers from overfitting on noisy datasets, by cutting rule terms or whole rules or by truncating decision trees according to certain metrics. There have been many pre-pruning mechanisms developed for the TDIDT approach, but for the Prism family the only existing pre-pruning facility is J-pruning. J-pruning not only works on Prism algorithms but also on TDIDT. Although it has been shown that J-pruning produces good results, this work points out that J-pruning does not use its full potential. The original J-pruning facility is examined and the use of a new pre-pruning facility, called Jmax-pruning, is proposed and evaluated empirically. A possible pre-pruning facility for TDIDT based on Jmax-pruning is also discussed.

eRules: a modular adaptive classification rule learning algorithm for data streams

Advances in hardware and software in the past decade allow to capture, record and process fast data streams at a large scale. The research area of data stream mining has emerged as a consequence from these advances in order to cope with the real time analysis of potentially large and changing data streams. Examples of data streams include Google searches, credit card transactions, telemetric data and data of continuous chemical production processes. In some cases the data can be processed in batches by traditional data mining approaches. However, in some applications it is required to analyse the data in real time as soon as it is being captured. Such cases are for example if the data stream is infinite, fast changing, or simply too large in size to be stored. One of the most important data mining techniques on data streams is classification. This involves training the classifier on the data stream in real time and adapting it to concept drifts. Most data stream classifiers are based on decision trees. However, it is well known in the data mining community that there is no single optimal algorithm. An algorithm may work well on one or several datasets but badly on others. This paper introduces eRules, a new rule based adaptive classifier for data streams, based on an evolving set of Rules. eRules induces a set of rules that is constantly evaluated and adapted to changes in the data stream by adding new and removing old rules. It is different from the more popular decision tree based classifiers as it tends to leave data instances rather unclassified than forcing a classification that could be wrong. The ongoing development of eRules aims to improve its accuracy further through dynamic parameter setting which will also address the problem of changing feature domain values.

Terminal: a miracle play with popular music from the end of the world

Terminal: A Miracle Play with Popular Music from the End of the World is a film and live performance project exploring the politics of post-apocalyptic fiction. A theatrical staging of a morality play for end times and future folk music, it recasts eschatology, as a foundational myth for a future society. Post-apocalyptic writing and cinema are grounded in an ethos of survivalism. Invoking Rousseau’s state of nature, or time before government, these fictions propose violent scenarios in which nuclear holocaust, environmental catastrophe and other disasters generate an individualistic politics of pure pragmatism, negating the possibility of democratic deliberation. Terminal narrates this familiar scenario, but at the same time questions its validity. The film, shot on black and white VHS at Kurt Schwitters’ Merzbarn in Cumbria, dramatises a series of conversations between future-historical archetypes about the needs and pressures of the situation in which they find themselves at the end of the world. The performers then gather to play worshipful songs about acid rain, radiation sickness and eating the dog, using a mix of conventional, obscure and makeshift instruments In the tradition of books such as Russell Hoban’s Riddley Walker and Arthur M. Miller Jr.’s A Canticle for Liebowitz, Terminal imagines artistic expression and new folk traditions for a world to come after the apocalypse. If, as Slavoj Žižek would have it, it is easier to imagine the end of the world than to think of the end of capitalism, the project juxtaposes these two endpoints to test out how alternative scenarios might emerge from the collaborative practice of making theatre and music against a setting of social collapse.

Boundaries and Bridges: the influence of James Cooksey Culwick on the development of the teaching and learning of music in nineteenth century Ireland

James Cooksey Culwick (1845-1907) was born in England. Trained as chorister and organist in Lichfield Cathedral, he moved to Ireland at twenty- one and remained until his death in 1907. Although his reputation as scholar, musician and teacher was acknowledged widely during his lifetime - he received an honorary doctorate from University of Dublin (1893) - little is known about the contribution he made to music education. This paper addresses this gap in the literature and argues that it was Culwick's singular achievement to pay attention to music pedagogy at secondary level, by recognizing that music could be seen as a serious career option for girls, and by providing resources for teachers which emphasised the development of an 'art-feeling' in pupils of all abilities. In addition, he considered Irish music as an art which had significance as music first, and Irish music second, and advocated a 'laudable tolerance' for opposing views on matters of cultural identity to Ireland at the end of the nineteenth century.