| 研究実績の概要 |
In year 2024, we continued working on the combination of neural networks and subspace learning. We have worked in an application to environmental sound classification, where we propose a method using an ensemble of subspace representations of latent features obtained from various neural network-based models. We were able to successfully achieve a competitive performance on real data, and published this result on the journal Applied Acoustics. We also developed a method for data analysis in a Riemannian geometry. We specifically proposed a time-series data embedding technique that preserves manifold curvature and orientation. We showcased our method in a setting with subspace representation, with an use case of analyzing the temporal information encoded in neural activation dynamics.
|
