Random forests with parametric entropy-based information gains for classification and regression problems.

The random forest algorithm is one of the most popular and commonly used algorithms for classification and regression tasks. It combines the output of multiple decision trees to form a single result. Random forest algorithms demonstrate the highest accuracy on tabular data compared to other algorithms in various applications.

Topic models with elements of neural networks: investigation of stability, coherence, and determining the optimal number of topics.

Topic modeling is a widely used instrument for the analysis of large text collections. In the last few years, neural topic models and models with word embeddings have been proposed to increase the quality of topic solutions. However, these models were not extensively tested in terms of stability and interpretability.

The transmission of pottery technology among prehistoric European hunter-gatherers.

Human history has been shaped by global dispersals of technologies, although understanding of what enabled these processes is limited. Here, we explore the behavioural mechanisms that led to the emergence of pottery among hunter-gatherer communities in Europe during the mid-Holocene. Through radiocarbon dating, we propose this dispersal occurred at a far faster rate than previously thought.

Current Siberian heating is unprecedented during the past seven millennia.

The Arctic is warming faster than any other region on Earth. Putting this rapid warming into perspective is challenging because instrumental records are often short or incomplete in polar regions and precisely-dated temperature proxies with high temporal resolution are largely lacking. Here, we provide this long-term perspective by reconstructing past summer temperature variability at Yamal Peninsula - a hotspot of recent warming - over the past 7638 years using annually resolved tree-ring records.