In this thesis, learning refers to the intelligent computational extraction of knowledge from data. Supervised learning tasks require data to be annotated with labels, whereas for unsupervised learning, data is not labelled. Semi-supervised learning deals with data sets that are partially labelled. A major issue with supervised and semi-supervised learning of data streams is late-arriving or missing class labels. Assuming that correctly labelled data will always be available and timely is often unfeasible, and, as such, supervised methods are not directly applicable in the real world. Therefore, real-world problems usually require the use of semi-supervised or unsupervised learning techniques. For instance, when considering a spam detection task, it is not reasonable to assume that all spam will be identified (correctly labelled) prior to learning. Additionally, in semi-supervised learning, "the instances having the highest [predictive] confidence are not necessarily the most useful ones" [41]. We investigate how self-training performs without its selective heuristic in a streaming setting. This leads us to our contributions. We extend an existing concept drift detector to operate without any labelled data, by using a sliding window of our ensemble's prediction confidence, instead of a boolean indicating whether the ensemble's predictions are correct. We also extend selective self-training, a semi-supervised learning method, by using all predictions, and not only those with high predictive confidence. Finally, we introduce a novel windowing type for ensembles, as sliding windows are very time consuming and regular tumbling windows are not a suitable replacement. Our windowing technique can be considered a hybrid of the two: we train each sub-classifier in the ensemble with tumbling windows, but delay training in such a way that only one sub-classifier can update its model per iteration. We found, through statistical significance tests, that our framework is (roughly 160 times) faster than current state of the art techniques, and achieves comparable predictive accuracy. That being said, more research is needed to further reduce the quantity of labelled data used for training, while also increasing its predictive accuracy.

Ip Kim Ho. / Thesis (M.Mus.)--Chinese University of Hong Kong, 1997.

In a wide range of applications, datasets are generated for which the number of variables p exceeds the sample size n. Penalised likelihood methods are widely used to tackle regression problems in these high-dimensional settings. In this thesis, we carry out an extensive empirical comparison of the performance of popular penalised regression methods in high-dimensional settings and propose new methodology that uses ensemble learning to enhance the performance of these methods. The relative efficacy of different penalised regression methods in finite-sample settings remains incompletely understood. Through a large-scale simulation study, consisting of more than 1,800 data-generating scenarios, we systematically consider the influence of various factors (for example, sample size and sparsity) on method performance. We focus on three related goals --- prediction, variable selection and variable ranking --- and consider six widely used methods. The results are supported by a semi-synthetic data example. Our empirical results complement existing theory and provide a resource to compare performance across a range of settings and metrics. We then propose a new ensemble learning approach for improving the performance of penalised regression methods, called STructural RANDomised Selection (STRANDS). The approach, that builds and improves upon the Random Lasso method, consists of two steps. In both steps, we reduce dimensionality by repeated subsampling of variables. We apply a penalised regression method to each subsampled dataset and average the results. In the first step, subsampling is informed by variable correlation structure, and in the second step, by variable importance measures from the first step. STRANDS can be used with any sparse penalised regression approach as the ``base learner''. In simulations, we show that STRANDS typically improves upon its base learner, and demonstrate that taking account of the correlation structure in the first step can help to improve the efficiency with which the model space may be explored. We propose another ensemble learning method to improve the prediction performance of Ridge Regression in sparse settings. Specifically, we combine Bayesian Ridge Regression with a probabilistic forward selection procedure, where inclusion of a variable at each stage is probabilistically determined by a Bayes factor. We compare the prediction performance of the proposed method to penalised regression methods using simulated data.

Pulsars are rapidly rotating neutron stars which emit a strong beam of energy through mechanisms that are not entirely clear to physicists. These very dense stars are used by astrophysicists to study many basic physical phenomena, such as the behavior of plasmas in extremely dense environments, behavior of pulsar-black hole pairs, and tests of general relativity. Many of these tasks require information to answer the scientific questions posed by physicists. In order to provide more pulsars to study, there are several large-scale pulsar surveys underway, which are generating a huge backlog of unprocessed data. Searching for pulsars is a very labor-intensive process, currently requiring skilled people to examine and interpret plots of data output by analysis programs. An automated system for screening the plots will speed up the search for pulsars by a very large factor. Research to date on using machine learning and pattern recognition has not yielded a completely satisfactory system, as systems with the desired near 100% recall have false positive rates that are higher than desired, causing more manual labor in the classification of pulsars. This work proposed to research, identify, propose and develop methods to overcome the barriers to building an improved classification system with a false positive rate of less than 1% and a recall of near 100% that will be useful for the current and next generation of large pulsar surveys. The results show that it is possible to generate classifiers that perform as needed from the available training data. While a false positive rate of 1% was not reached, recall of over 99% was achieved with a false positive rate of less than 2%. Methods of mitigating the imbalanced training and test data were explored and found to be highly effective in enhancing classification accuracy.

Ämnet prestationsångest attackeras från många vinklar och är något som de allra flesta kan känna igen sig i. I denna studie fördjupar jag mig i förhållandet mellan prestationsångest och individens upplevelse av hur det är att musicera med andra. Studien inriktar sig mot musikstudenters relation till prestationsångest i undervisning och ensemblespel, med syftet att belysa begreppet Music Performance Anxiety (MPA). Genom fokusgruppsintervju och deltagarobservation har jag tagit fram underlag samt kartlagt hur deras upplevelse av MPA ter sig i musikämnet och i ensemblesammanhang. Hur skiljer sig upplevelsen av detta i ensemblesammanhang från individuella sammanhang och hur skiljer sig känslan av MPA i undervisning i jämförelse med andra musikutövande sammanhang? Genom kvalitativ data och analys av deltagarnas egna erfarenheter och upplevelser har studien lett fram till en djupare inblick i hur dessa individer upplever prestationsångest i musiksammanhang, samt hur den sociala aspekten av att musicera får en betydande roll när ämnet ska belysas. Generellt uppnådde samtliga deltagare kriterierna för en mer eller mindre utvecklad form av MPA och den generella uppfattningen var att de inte fått några verktyg eller arbetat med ämnet prestationsångest kontinuerligt i sina pågående eller föregående studier. Min uppfattning är därför att vidare forskning kring detta ämne behövs för att konkretisera, och på ett ett bättre sätt, kartlägga känslor och sociala strukturer som hämmar studenters musikaliska utveckling såväl som det konstnärliga uttrycket.

abstract: Para Mi Alma is a composition for chamber wind ensemble comprised of an Introduction, two dance movements, and a concluding movement featuring the full ensemble in a chorale-like finale. This piece follows the narrative of an abusive relationship, and the emotional rollercoaster that one experiences during the self extrication and consequential rebirth of identity. Para Mi Alma (For My Soul) is scored for chamber wind ensemble with the following instrumentation: piccolo/flute, Bb clarinet, bass clarinet, bassoon; soprano, tenor, and baritone saxophone; trumpet, trumpet/flugelhorn, horn in F, tenor and bass trombone; double bass, and three percussionists - marimba/congas, auxiliary percussion (wind chimes, suspended cymbal, triangle, bass drum, snare drum, double cowbell, tam-tam), and timpani/timbales. The duration of this work is approximately 11’00”. Each movement portrays a stage in the relationship, and the mental state of the person experiencing abuse. The Introduction begins with a piccolo solo and marimba accompaniment, and gradually builds to the full ensemble; this section of music illustrates the moment that relational ties to the transgressor are cut — a split second of clarity and space before the spiral of anxiety and overwhelming thoughts of self deprecation invade. Movement I is a salsa, representing the dance of two people entering into a relationship. The meter changes and hemiolas serve to upset the underlying groove and create rhythmic tension, while the surface of the music appears unscathed. Finally the dance is interrupted by an aggressive bass solo, which initiates the transition to Movement II. This transition serves to remind the listener of the Introduction, and the dissolution of the relationship; it is characterized by chaos and confused clusters of melodic lines and dissonant harmonies. Movement II is a tango, representative of the emotional extremes of heartbreak, anger, confusion, and shame. The conclusion of the Tango directly segues into Movement III, which features a short brass chorale before building to include the full ensemble. Movement III portrays the support system of family and friends, and personifies the collective effort that takes place in healing and growth. / Dissertation/Thesis / Masters Thesis Music 2019

No description available.

Clustering large data sets recently has emerged as an important area of research. The ever-increasing size of data sets and poor scalability of clustering algorithms has drawn attention to distributed clustering for partitioning large data sets. Sometimes, centrally pooling the distributed data is also expensive. There might be also constraints on data sharing between different distributed locations due to privacy, security, or proprietary nature of the data. In this work we propose an algorithm to cluster large-scale data sets without centrally pooling the data. Data at distributed sites are clustered independently i.e. without any communication among them. After partitioning the local/distributed sites we send only the centroids of each site to a central location. Thus there is very little bandwidth cost in a wide area network scenario. The distributed sites/subsets neither exchange cluster labels nor individual data features thus providing the framework for privacy preserving distributive clustering. Centroids from each local site form an ensemble of centroids at the central site. Our assumption is that data in all distributed locations are from the same underlying distribution and the set of centroids obtained by partitioning the data in each subset/distributed location gives us partial information about the position of the cluster centroids in that distribution. Now, the problem of finding a global partition using the limited knowledge of the ensemble of centroids can be viewed as the problem of reaching a global consensus on the position of cluster centroids. A global consensus on the position of cluster centroids of the global data using only the very limited statistics of the position of centroids from each local site is reached by grouping the centroids into consensus chains and computing the weighted mean of centroids in a consensus chain to represent a global cluster centroid. We compute the Euclidean distance of each example from the global set of centroids, and assign it to the centroid nearest to it. Experimental results show that quality of clusters generated by our algorithm is similar to the quality of clusters generated by clustering all the data at a time. We have shown that the disputed examples between the clusters generated by our algorithm and clustering all the data at a time lay on the border of clusters as expected. We also proposed a centroid-filtering algorithm to make partitions formed by our algorithm better.

Etant donné un point fixe pour un homéomorphisme de surface, on peut définir un ensemble de rotation autour du point fixe, qui est un invariant de conjugaison locale. Ce mémoire commence l'étude de cet invariant et de ses liens avec d'autres propriétés dynamiques : en particulier l'existence d'orbites périodiques, la différentiabilité au point fixe, l'indice de Poincaré-Lefschetz lorsque le point fixe est isolé.

<p>I arbetet studeras möjligheten att använda inspelningsteknik som ett verktyg i en kreativ musikalisk process, som en hjälp för att analysera och bedöma musikers insatser för att tydliggöra och förbättra prestationen. Studien behandlar frågan om inspelningar kan vara ett aktivt hjälpmedel vid komposition och om det är möjligt att använda i formellt pedagogiska miljöer för individuell utveckling och ensemblespel. Studien har genomförts vid ett tillfälle, med fyra musiker som utifrån ett grundmaterial, improviserat, arrangerat och spelat in en låt tillsammans. Inspelningarna har gjorts i en studio med datorbaserad inspelningsteknik och analyserats och värderats utifrån studiens syfte och presenteras tillsammans med en ljudinspelning på CD med material från inspelningen. Reflektion och bedömning av materialet och metoden har skett i samtal mellan musikerna under inspelningssessionen. Resultatet från inspelningen visar att metoden kan vara ett funktionellt hjälpmedel för musiker i syfte att reflektera över den egna och medmusikanternas insatser vid exempelvis repetitioner. Användningsområdet inkluderar skolans musikundervisning med fokus på ensemblespel.</p>