On spatially correlated observations in importance sampling methods for subsidence estimation

The particle filter is a data assimilation method based on importance sampling for state and parameter estimation. We apply a particle filter in two different quasi-static experiments with models of subsidence caused by a compacting reservoir. The first model considers uncorrelated model state variables and observations, with observed...

Increasing trust in complex machine learning systems: Studies in the music domain

Machine learning (ML) has become a core technology for many real-world applications. Modern ML models are applied to unprecedentedly complex and difficult challenges, including very large and subjective problems. For instance, applications towards multimedia understanding have been advanced substantially. Here, it is already prevalent that...

Mosaic Garden City: redefining the relation between people and nature by structuring water management through landscape infrastructure in an informal settlement, Kampung Tamansari in Bandung

Slum population has increased continuously in global south. It expands onto precarious land such as floodplains, lagoon areas and so on leading to deficiency of basic facilities. Bandung is the third most populous city in Indonesia with around 26,000 slum dwellings. Kampung Tamansari in Bandung is the densest informal settlement located along...

Are Nearby Neighbors Relatives?: Testing Deep Music Embeddings

Deep neural networks have frequently been used to directly learn representations useful for a given task from raw input data. In terms of overall performance metrics, machine learning solutions employing deep representations frequently have been reported to greatly outperform those using hand-crafted feature representations. At the same time,...

One deep music representation to rule them all? A comparative analysis of different representation learning strategies

Inspired by the success of deploying deep learning in the fields of Computer Vision and Natural Language Processing, this learning paradigm has also found its way into the field of Music Information Retrieval. In order to benefit from deep learning in an effective, but also efficient manner, deep transfer learning has become a common approach...

Transfer Learning of Artist Group Factors to Musical Genre Classification

The automated recognition of music genres from audio information is a challenging problem, as genre labels are subjective and noisy. Artist labels are less subjective and less noisy, while certain artists may relate more strongly to certain genres. At the same time, at prediction time, it is not guaranteed that artist labels are available for a...