Showcasing the TAIAO project: providing resources for machine learning from images of New Zealand's natural environment.

Proper management of the earth's natural resources is imperative to combat further degradation of the natural environment. However, the environmental datasets necessary for informed resource planning and conservation can be costly to collect and annotate. Consequently, there is a lack of publicly available datasets, particularly annotated image datasets relevant for environmental conservation, that can be used for the evaluation of machine learning algorithms to determine their applicability in real-world scenarios.

Experiments in cross-domain few-shot learning for image classification.

Cross-domain few-shot learning has many practical applications. This paper attempts to shed light on suitable configurations of feature exactors and 'shallow' classifiers in this machine learning setting. We apply ResNet-based feature extractors pretrained on two versions of the ImageNet dataset to five target domains with different degrees of similarity to ImageNet, varying the feature extractor size, the network stage at which features are extracted, and the learning algorithm applied to the extracted features.

Privacy protection for health information research in New Zealand district health boards.

Aim: To examine the practices used by New Zealand's 20 district health boards (DHBs) to protect patient privacy when patient information is used for research, and particularly practices for de-identifying information.

Method: An e-mailed questionnaire survey, using New Zealand's Official Information Act to request information on the policies and practices of each DHB.

Results: 19/20 DHBs (95%) responded to the survey, one of which reported that it did not provide patient information for research.

Active learning with drifting streaming data.

In learning to classify streaming data, obtaining true labels may require major effort and may incur excessive cost. Active learning focuses on carefully selecting as few labeled instances as possible for learning an accurate predictive model. Streaming data poses additional challenges for active learning, since the data distribution may change over time (concept drift) and models need to adapt.