ﻻ يوجد ملخص باللغة العربية
Embodied cognition states that semantics is encoded in the brain as firing patterns of neural circuits, which are learned according to the statistical structure of human multimodal experience. However, each human brain is idiosyncratically biased, according to its subjective experience history, making this biological semantic machinery noisy with respect to the overall semantics inherent to media artifacts, such as music and language excerpts. We propose to represent shared semantics using low-dimensional vector embeddings by jointly modeling several brains from human subjects. We show these unsupervised efficient representations outperform the original high-dimensional fMRI voxel spaces in proxy music genre and language topic classification tasks. We further show that joint modeling of several subjects increases the semantic richness of the learned latent vector spaces.
Music semantics is embodied, in the sense that meaning is biologically mediated by and grounded in the human body and brain. This embodied cognition perspective also explains why music structures modulate kinetic and somatosensory perception. We leve
Mathematical approaches to modeling the mind since the 1950s are reviewed. Difficulties faced by these approaches are related to the fundamental incompleteness of logic discovered by K. Godel. A recent mathematical advancement, dynamic logic (DL) ove
The assessment of music performances in most cases takes into account the underlying musical score being performed. While there have been several automatic approaches for objective music performance assessment (MPA) based on extracted features from b
Convolutional neural networks (CNN) recently gained notable attraction in a variety of machine learning tasks: including music classification and style tagging. In this work, we propose implementing intermediate connections to the CNN architecture to
Deep representation learning offers a powerful paradigm for mapping input data onto an organized embedding space and is useful for many music information retrieval tasks. Two central methods for representation learning include deep metric learning an