This paper describes a solution to the AAIA'18 data mining challenge, which concerns prediction of win rates for decks in Hearthstone collectible card game. A neural network model assigning win rate to decks is learned based on maximisation of log probability of observed match results. A representation of deck contents is based on a second network, which performs the role of a dual-task encoder. Two tasks learned by the encoding networks are encoding decks in such a way that the full deck can be reconstructed, and encoding individual cards so that their specific properties can be decoded. Shared representation for these tasks allows the knowledge of individual cards to be taken into account.
In this paper, a solution to ESENSEI data mining challenge concerning the analysis of microscopic hair images is described. The task of the challenge was to detect locations of hair follicles in closeup images of a human scalp. The proposed solution is based on a convolutional neural network architecture. To improve generalization performance, we enhance training and test datasets using image transformations applied to both input and output. The chosen transformations are two axis symmetries and switching axes, all of which are possible to apply regardless of resolution without producing interpolation artifacts. Since these can be combined, 2 3 = 8 possible views of each image can be created to expand both training and test data. We demonstrate the effects of dataset enhancement in both training and classifying on results achievable on the competition dataset. The solution placed 2nd in the final challenge evaluation.
Automatic retrieval of music information is an active area of research in which problems such as automatically assigning genres or descriptors of emotional content to music emerge. Recent advancements in the area rely on the use of deep learning, which allows researchers to operate on a low-level description of the music. Deep neural network architectures can learn to build feature representations that summarize music files from data itself, rather than expert knowledge. In this paper, a novel approach to applying feature learning in combination with support vector machines to musical data is presented. A spectrogram of the music file, which is too complex to be processed by SVM, is first reduced to a compact representation by a recurrent neural network. An adjustment to loss function of the network is proposed so that the network learns to build a representation space that replicates a certain notion of similarity between annotations, rather than to explicitly make predictions. We evaluate the approach on five datasets, focusing on emotion recognition and complementing it with genre classification. In experiments, the proposed loss function adjustment is shown to improve results in classification and regression tasks, but only when the learned similarity notion corresponds to a kernel function employed within the SVM. These results suggest that adjusting deep learning methods to build data representations that target a specific classifier or regressor can open up new perspectives for the use of standard machine learning methods in music domain.
This paper concerns the retrieval of audio samples with a high degree of user interaction, motivated by a practical use case. We consider an open set recognition scenario in which the goal is to find all occurrences of a subjectively interesting sound selected by a user within a particular audio file. We use only a single starting example and maintain interaction through yes-no answers from the user, indicating whether any new retrieved sound matches the target pattern. We present a small dataset for this task and evaluate a baseline solution based on Nonnegative Matrix Factorization and greedy feature selection.
Abstract-The paper concerns automatic recognition of emotion induced by music (MER, Music Emotion Recognition).Comparison of different sparse coding schemes in a task of MER is the main contribution of the paper. We consider a domainspecific categorization of emotions, called Geneva Emotional Music Scale (GEMS), which focuses on induced emotions rather than expressed emotions. We were able to find only one dataset, namely Emotify, in which data are annotated with GEMS categories, this set was used in our experiments. Our main goal was to compare different sparse coding approaches in a task of learning features useful for predicting musically induced emotions, taking into account categories present in the GEMS. We compared five sparse coding methods and concluded that sparse autoencoders outperform other approaches.
Institute of Mathematics of the Academy of Sciences of the Czech Republic provides access to digitized documents strictly for personal use. Each copy of any part of this document must contain these Terms of use. This paper has been digitized, optimized for electronic delivery and stamped with digital signature within the project DML-CZ: The Czech Digital Mathematics Library http://project.dml.cz Časopis pro pěstování matematiky, rol. 91 (1966), Praha REFERÁTY SUMMER SESSION ON ORDERED SETS AT CIKHAJ From August 23 to 31,1965, the mathematical departments of Brno and Bratislava universities in cooperation with the Czechoslovak Academy of Sciences, organized at Cikhaj a summer session on ordered sets and abstract algebra. 26 mathematicians took part in this summer session, and 11 lectures were given. The contents of all these lectures are presented here; on behalf of J. Jakubik, who was absent the lecture was read by K. Molnarova. DIE DEDEKINDSCHEN SCHNITTE IM DIREKTEN PRODUKT VON HALBGEORDNETEN MENGEN J. JAKUBIK, Kosice Es sei G 4= 0 eine halbgeordnete Menge. Für A c G bezeichnen wir mit L(A) bzw. U(A) die Menge aller unteren Schranken bzw. aller oberen Schranken von A. Ferner sei D(G) bzw. E(G) das System aller Mengen L(U(A)) 9 wobei A eine beliebige Teil menge von G bzw. eine beliebige nichtleere nach oben begrenzte Teilmenge von G ist. Jedes der Systeme D(G) 9 E(G) ist durch die mengentheoretische Inklusion teilweise geordnet. Es ist bekannt, dass D(G) ein vollständiger Verband ist; E(G) ist im all gemeinen kein Verband. Wir bezeichnen mit I7G a das direkte Produkt der halbgeord neten Mengen G a. Es gilt der Satz: (1) Aus dem Isomorphismus G ~ ÜG a folgt die Existenz eines Isomorphismus E(G) ~ II E(G a). Eine analoge Behauptung für D anstatt E gilt nicht. Ferner sei G eine gerichtete vollständig abgeschlossene Gruppe. Es ist bekannt, dass E(G) im solchen Fall eine vollständige verbandsgeordnete Gruppe ist. Es gilt ein analoger Satz zu (1): Es sei G eine gerichtete vollständig abgeschlossene Gruppe* die mit dem direkten Produkt der halbgeordneten Gruppen G a isomorph ist. Dann ist E(G) mit dem direkten Produkt der verbandsgeordneten Gruppen E(G a) iso morph.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.