Deep generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have recently been applied to style and domain transfer for images, and in the case of VAEs, music. GAN-based models employing several generators and some form of cycle consistency loss have been among the most successful for image domain transfer. In this paper we apply such a model to symbolic music and show the feasibility of our approach for music genre transfer. Evaluations using separate genre classifiers show that the style transfer works well. In order to improve the fidelity of the transformed music, we add additional discriminators that cause the generators to keep the structure of the original music mostly intact, while still achieving strong genre transfer. Visual and audible results further show the potential of our approach. To the best of our knowledge, this paper represents the first application of GANs to symbolic music domain transfer.
Activity recognition using off-the-shelf smartwatches is an important problem in humanactivity recognition. In this paper, we present an end-to-end deep learning approach, able to provideprobability distributions over activities from raw sensor data. We apply our methods to 10 complexfull-body exercises typical in CrossFit, and achieve a classification accuracy of 99.96%. We additionallyshow that the same neural network used for exercise recognition can also be used in repetitioncounting. To the best of our knowledge, our approach to repetition counting is novel and performswell, counting correctly within an error of 1 repetitions in 91% of the performed sets.
The largest gap in the list of reciprocal interatomic distances is used to limit the coordination polyhedra. For the structure types AIB2 and NiAs, the polyhedra are evaluated according to c/a. In plots of c/a versus rA/rB, the various coordination types correspond to actually observed families of representatives. These results as well as others from more than 50 structure types support the view that coordination as limited by the largest gap is a realistic factor.
Coordination sequences (CS) have been calculated for all approved zeolite topologies, all dense SiO 2 polymorphs and 16 selected non-tetrahedral structures and the algebraic structure of these CS's has been analyzed. Two algebraic descriptions of coordination sequences are presented. One description uses periodic sets of quadratic equations and is already established in the literature. The second description employs generating functions, which are well known in combinatorics but are used here for the first time in connection with coordination sequences. The algebraic analysis based on generating functions turns out to be more powerful than the other approach. Based on the algebraic analyses, exact topological densities are derived and tabulated for all the structures investigated. In addition, 'n-dimensional sodalite' is observed to have an especially simple n-dimensional graph.
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.