Aggregation Cross-Entropy (ACE)
In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective. The ACE loss function exhibits competitive performance to CTC and the attention mechanism, with much quicker implementation (as it involves only four fundamental formulas), faster inference\back-propagation (approximately O(1) in parallel), less storage requirement (no parameter and negligible runtime memory), and convenient employment (by replacing CTC with ACE). Furthermore, the proposed ACE loss function exhibits two noteworthy properties: (1) it can be directly applied for 2D prediction by flattening the 2D prediction into 1D prediction as the input and (2) it requires only characters and their numbers in the sequence annotation for supervision, which allows it to advance beyond sequence recognition, e.g., counting problem. The code is publicly available at https://…/Aggregation-Cross-Entropy. …

NL4Py
NL4Py is a NetLogo controller software for Python, for the rapid, parallel execution of NetLogo models. NL4Py provides both headless (no graphical user interface) and GUI NetLogo workspace control through Python. Spurred on by the increasing availability of open-source computation and machine learning libraries on the Python package index, there is an increasing demand for such rapid, parallel execution of agent-based models through Python. NetLogo, being the language of choice for a majority of agent-based modeling driven research projects, requires an integration to Python for researchers looking to perform statistical analyses of agent-based model output using these libraries. Unfortunately, until the recent introduction of PyNetLogo, and now NL4Py, such a controller was unavailable. This article provides a detailed introduction into the usage of NL4Py and explains its client-server software architecture, highlighting architectural differences to PyNetLogo. A step-by-step demonstration of global sensitivity analysis and parameter calibration of the Wolf Sheep Predation model is then performed through NL4Py. Finally, NL4Py’s performance is benchmarked against PyNetLogo and its combination with IPyParallel, and shown to provide significant savings in execution time over both configurations. …

COBRAS-TS
Clustering is ubiquitous in data analysis, including analysis of time series. It is inherently subjective: different users may prefer different clusterings for a particular dataset. Semi-supervised clustering addresses this by allowing the user to provide examples of instances that should (not) be in the same cluster. This paper studies semi-supervised clustering in the context of time series. We show that COBRAS, a state-of-the-art semi-supervised clustering method, can be adapted to this setting. We refer to this approach as COBRAS-TS. An extensive experimental evaluation supports the following claims: (1) COBRAS-TS far outperforms the current state of the art in semi-supervised clustering for time series, and thus presents a new baseline for the field; (2) COBRAS-TS can identify clusters with separated components; (3) COBRAS-TS can identify clusters that are characterized by small local patterns; (4) a small amount of semi-supervision can greatly improve clustering quality for time series; (5) the choice of the clustering algorithm matters (contrary to earlier claims in the literature). …

DEDPUL
This paper studies Positive-Unlabeled Classification, the problem of semi-supervised binary classification in the case when Negative (N) class in the training set is contaminated with instances of Positive (P) class. We develop a novel method (DEDPUL) that simultaneously solves two problems concerning the contaminated Unlabeled (U) sample: estimates the proportions of the mixing components (P and N) in U, and classifies U. By conducting experiments on synthetic and real-world data we favorably compare DEDPUL with current state-of-the-art methods for both problems. We introduce an automatic procedure for DEDPUL hyperparameter optimization. Additionally, we improve two methods in the literature and achieve DEDPUL level of performance with one of them. …