Deep learning methods may decline in their performance when the number of labelled training samples is limited, in a scenario known as few-shot learning. The methods may even degrade the accuracy in classifying instances of classes that have not been seen previously, called zero-shot learning. While the classification results achieved by the zero-shot learning methods are steadily improved, different problem settings, and diverse experimental setups have emerged. It becomes difficult to measure fairly the effectiveness of each proposed method, thus hindering further research in the field. In this article, a comprehensive survey is given on the methodology, implementation, and fair evaluations for practical and applied computing facets on the recent progress of zero-shot learning.

In obesity studies, several researchers have been applying machine learning tools to identify factors affecting human body weight. However, a proper review of strength, limitations and evaluation metrics of machine learning algorithms in obesity is lacking. This study reviews the status of application of machine learning algorithms in obesity studies and to identify strength and weaknesses of these methods. A scoping review of paper focusing on obesity was conducted. PubMed and Scopus databases were searched for the application of machine learning in obesity using different keywords. Only English papers in adult obesity between 2014 and 2019 were included. Also, only papers that focused on controllable factors (e.g., nutrition intake, dietary pattern and/or physical activity) were reviewed in depth. Papers on genetic or childhood obesity were excluded. Twenty reviewed papers used machine learning algorithms to identify the relationship between the contributing factors and obesity. Regression algorithms were widely applied. Other algorithms such as neural network, random forest and deep learning were less exploited. Limitations regarding data priori assumptions, overfitting and hyperparameter optimization were discussed. Performance metrics and validation techniques were identified. Machine learning applications are positively impacting obesity research. The nature and objective of a study and available data are key factors to consider in selecting the appropriate algorithms. The future research direction is to further explore and take advantage of the modern methods, i.e., neural network and deep learning, in obesity studies.

Multilabel learning is an important topic in machine learning research. Evaluating models in multilabel settings requires specific cross validation methods designed for multilabel data. In this article, we show that the most widely used cross validation split quality measure does not behave adequately with multilabel data that has strong class imbalance. We present improved measures and an algorithm, optisplit, for optimizing cross validations splits. Extensive comparison of various types of cross validation methods shows that optisplit produces more even cross validation splits than the existing methods and it is among the fastest methods with good splitting performance.

We present a method to construct optimal clustering via a sequence of merge steps. We formulate the merge-based clustering as a minimum redundancy search tree, and then search the optimal clustering by a branch-and-bound technique. Optimal clustering is found regardless of the objective function used. We also consider two suboptimal polynomial time variants based on the proposed branch-and-bound technique. However, all variants are slow and has merely theoretical interest. We discuss the reasons for the results.

Definition modeling, the task of generating a definition for a given term, is a relatively new area of research applied in evaluating word embeddings. Automatic generation of dictionary quality definitions has many applications in natural language processing, such as sentiment analysis, machine translation, and word sense disambiguation. Additionally, definition modeling is also helpful for evaluating the quality of word embeddings. As more research is done in this field, the need for a summary of different applications, approaches, and obstacles grows apparent. This review provides an overview of the current research in definition modeling and a list of future directions and trends.