This study proposes a novel hybrid learning approach for developing a visual path-following algorithm for industrial robots. The process involves three steps: data collection from a simulation environment, network training, and testing on a real robot. The actor network is trained using supervised learning for 500 epochs. A semitrained network is then obtained at the $250^{th}$ epoch. This network is further trained for another 250 epochs using reinforcement learning methods within the simulation environment. Networks trained with supervised learning (500 epochs) and the proposed hybrid learning method (250 epochs each of supervised and reinforcement learning) are compared. The hybrid learning approach achieves a significantly lower average error (30.9 mm) compared with supervised learning (39.3 mm) on real-world images. Additionally, the hybrid approach exhibits faster processing times (31.7 s) compared with supervised learning (35.0 s). The proposed method is implemented on a KUKA Agilus KR6 R900 six-axis robot, demonstrating its effectiveness. Furthermore, the hybrid approach reduces the total power consumption of the robot’s motors compared with the supervised learning method. These results suggest that the hybrid learning approach offers a more effective and efficient solution for visual path following in industrial robots compared with traditional supervised learning.

Novel prediction methods should always be compared to a baseline to determine their performance. Without this frame of reference, the performance score of a model is basically meaningless. What does it mean when a model achieves an $F_1$ of 0.8 on a test set? A proper baseline is, therefore, required to evaluate the ‘goodness’ of a performance score. Comparing results with the latest state-of-the-art model is usually insightful. However, being state-of-the-art is dynamic, as newer models are continuously developed. Contrary to an advanced model, it is also possible to use a simple dummy classifier. However, the latter model could be beaten too easily, making the comparison less valuable. Furthermore, most existing baselines are stochastic and need to be computed repeatedly to get a reliable expected performance, which could be computationally expensive. We present a universal baseline method for all binary classification models, named the Dutch Draw (DD). This approach weighs simple classifiers and determines the best classifier to use as a baseline. Theoretically, we derive the DD baseline for many commonly used evaluation measures and show that in most situations it reduces to (almost) always predicting either zero or one. Summarizing, the DD baseline is general, as it is applicable to any binary classification problem; simple, as it can be quickly determined without training or parameter tuning; and informative, as insightful conclusions can be drawn from the results. The DD baseline serves two purposes. First, it is a robust and universal baseline that enables comparisons across research papers. Second, it provides a sanity check during the prediction model’s development process. When a model does not outperform the DD baseline, it is a major warning sign.

Oceans will play a crucial role in our efforts to combat the growing climate emergency. Researchers have proposed several strategies to harness greener energy through oceans and use oceans as carbon sinks. However, the risks these strategies might pose to the ocean and marine ecosystem are not well understood. It is imperative that we quickly develop a range of tools to monitor ocean processes and marine ecosystems alongside the technology to deploy these solutions on a large scale into the oceans. Large arrays of inexpensive cameras placed deep underwater coupled with machine learning pipelines to automatically detect, classify, count, and estimate fish populations have the potential to continuously monitor marine ecosystems and help study the impacts of these solutions on the ocean. In this paper, we successfully demonstrate the application of YOLOv4 and YOLOv7 deep learning models to classify and detect six species of fish in a dark artificially lit underwater video dataset captured 500 m below the surface, with a mAP of 76.01% and 85.0%, respectively. We show that 2,000 images per species, for each of the six species of fish is sufficient to train a machine-learning species classification model for this low-light environment. This research is a first step toward systems to autonomously monitor fish deep underwater while causing as little disruption as possible. As such, we discuss the advances that will be needed to apply such systems on a large scale and propose several avenues of research toward this goal.

A standard text-as-data workflow in the social sciences involves identifying a set of documents to be labeled, selecting a random sample of them to label using research assistants, training a supervised learner to label the remaining documents, and validating that model’s performance using standard accuracy metrics. The most resource-intensive component of this is the hand-labeling: carefully reading documents, training research assistants, and paying human coders to label documents in duplicate or more. We show that hand-coding an algorithmically selected rather than a simple-random sample can improve model performance above baseline by as much as 50%, or reduce hand-coding costs by up to two-thirds, in applications predicting (1) U.S. executive-order significance and (2) financial sentiment on social media. We accompany this manuscript with open-source software to implement these tools, which we hope can make supervised learning cheaper and more accessible to researchers.

We live in a world of text. Yet the sheer magnitude of social media data, coupled with a need to measure complex psychological constructs, has made this important source of data difficult to use. Researchers often engage in costly hand coding of thousands of texts using supervised techniques or rely on unsupervised techniques where the measurement of predefined constructs is difficult. We propose a novel approach that we call ‘super-unsupervised’ learning and demonstrate its usefulness by measuring the psychologically complex construct of online political hostility based on a large corpus of tweets. This approach accomplishes the feat by combining the best features of supervised and unsupervised learning techniques: measurements of complex psychological constructs without a single labelled data source. We first outline the approach before conducting a diverse series of tests that include: (i) face validity, (ii) convergent and discriminant validity, (iii) criterion validity, (iv) external validity, and (v) ecological validity.

This paper focuses on automatically assessing language proficiency levels according to linguistic complexity in learner English. We implement a supervised learning approach as part of an automatic essay scoring system. The objective is to uncover Common European Framework of Reference for Languages (CEFR) criterial features in writings by learners of English as a foreign language. Our method relies on the concept of microsystems with features related to learner-specific linguistic systems in which several forms operate paradigmatically. Results on internal data show that different microsystems help classify writings from A1 to C2 levels (82% balanced accuracy). Overall results on external data show that a combination of lexical, syntactic, cohesive and accuracy features yields the most efficient classification across several corpora (59.2% balanced accuracy).

We introduce and assess the use of supervised learning in cross-domain topic classification. In this approach, an algorithm learns to classify topics in a labeled source corpus and then extrapolates topics in an unlabeled target corpus from another domain. The ability to use existing training data makes this method significantly more efficient than within-domain supervised learning. It also has three advantages over unsupervised topic models: the method can be more specifically targeted to a research question and the resulting topics are easier to validate and interpret. We demonstrate the method using the case of labeled party platforms (source corpus) and unlabeled parliamentary speeches (target corpus). In addition to the standard within-domain error metrics, we further validate the cross-domain performance by labeling a subset of target-corpus documents. We find that the classifier accurately assigns topics in the parliamentary speeches, although accuracy varies substantially by topic. We also propose tools diagnosing cross-domain classification. To illustrate the usefulness of the method, we present two case studies on how electoral rules and the gender of parliamentarians influence the choice of speech topics.

Supervised machine learning methods are increasingly employed in political science. Such models require costly manual labeling of documents. In this paper, we introduce active learning, a framework in which data to be labeled by human coders are not chosen at random but rather targeted in such a way that the required amount of data to train a machine learning model can be minimized. We study the benefits of active learning using text data examples. We perform simulation studies that illustrate conditions where active learning can reduce the cost of labeling text data. We perform these simulations on three corpora that vary in size, document length, and domain. We find that in cases where the document class of interest is not balanced, researchers can label a fraction of the documents one would need using random sampling (or “passive” learning) to achieve equally performing classifiers. We further investigate how varying levels of intercoder reliability affect the active learning procedures and find that even with low reliability, active learning performs more efficiently than does random sampling.