All recipes, no matter their contents and level of difficulty, follow a certain structure to an extend. It includes the recipe name, the ingredients and the instructions. All the recipes we will use will include this information. On top of that, recipes can be seen as a sequence of characters which makes them great inputs to characterlevel Recurrent neural networks as well as autoregressive models like the GPT-2 transformer. We would like to train the models on existing recipes and then have them recommend brand new ones. In the following experiments, we will make use of a transformer, more specifically a pre-trained GPT-2 model in order to generate structured recipes from scratch. For all this, we are going to be using a brand new dataset we created, from publicly available data. The novel dataset we create features specifically "fine-dining" recipes and the model is specifically fine-tuned to generate "gourmet" dishes unlike all the previous "normal" recipe models.

Social scientists often classify text documents to use the resulting labels as an outcome or a predictor in empirical research. Automated text classification has become a standard tool, since it requires less human coding. However, scholars still need many human-labeled documents to train automated classifiers. To reduce labeling costs, we propose a new algorithm for text classification that combines a probabilistic model with active learning. The probabilistic model uses both labeled and unlabeled data, and active learning concentrates labeling efforts on difficult documents to classify. Our validation study shows that the classification performance of our algorithm is comparable to state-of-the-art methods at a fraction of the computational cost. Moreover, we replicate two recently published articles and reach the same substantive conclusions with only a small proportion of the original labeled data used in those studies. We provide activeText, an open-source software to implement our method.

Personalized federated learning considers learning models unique to each client in a heterogeneous network. The resulting client-specific models have been purported to improve metrics such as accuracy, fairness, and robustness in federated networks. However, despite a plethora of work in this area, it remains unclear: (1) which personalization techniques are most effective in various settings, and (2) how important personalization truly is for realistic federated applications. To better answer these questions, we propose Motley, a benchmark for personalized federated learning. Motley consists of a suite of cross-device and cross-silo federated datasets from varied problem domains, as well as thorough evaluation metrics for better understanding the possible impacts of personalization. We establish baselines on the benchmark by comparing a number of representative personalized federated learning methods. These initial results highlight strengths and weaknesses of existing approaches, and raise several open questions for the community. Motley aims to provide a reproducible means with which to advance developments in personalized and heterogeneity-aware federated learning, as well as the related areas of transfer learning, meta-learning, and multi-task learning.

In this paper, we reveal that the rarity of safety-critical events in high-dimensional driving environments is the root cause of the safety challenge for autonomous vehicle development. We formulate it as "curse of rarity" (CoR) because it occurs ubiquitously in various safety-critical systems such as medical diagnosis and aerospace systems.

Performance comparison of supervised machine learning (ML) models are widely done in terms of different confusion matrix based scores obtained on test datasets. However, a dataset comprises several instances having different difficulty levels. Therefore, it is more logical to compare effectiveness of ML models on individual instances instead of comparing scores obtained for the entire dataset. In this paper, an alternative approach is proposed for direct comparison of supervised ML models in terms of individual instances within the dataset. A direct comparison matrix called \emph{Prayatul Matrix} is introduced, which accounts for comparative outcome of two ML algorithms on different instances of a dataset. Five different performance measures are designed based on prayatul matrix. Efficacy of the proposed approach as well as designed measures is analyzed with four classification techniques on three datasets. Also analyzed on four large-scale complex image datasets with four deep learning models namely ResNet50V2, MobileNetV2, EfficientNet, and XceptionNet. Results are evident that the newly designed measure are capable of giving more insight about the comparing ML algorithms, which were impossible with existing confusion matrix based scores like accuracy, precision and recall.

As free online encyclopedias with massive volumes of content, Wikipedia and Wikidata are key to many Natural Language Processing (NLP) tasks, such as information retrieval, knowledge base building, machine translation, text classification, and text summarization. In this paper, we introduce WikiDes, a novel dataset to generate short descriptions of Wikipedia articles for the problem of text summarization. The dataset consists of over 80k English samples on 6987 topics. We set up a two-phase summarization method - description generation (Phase I) and candidate ranking (Phase II) - as a strong approach that relies on transfer and contrastive learning. For description generation, T5 and BART show their superiority compared to other small-scale pre-trained models. By applying contrastive learning with the diverse input from beam search, the metric fusion-based ranking models outperform the direct description generation models significantly up to 22 ROUGE in topic-exclusive split and topic-independent split. Furthermore, the outcome descriptions in Phase II are supported by human evaluation in over 45.33% chosen compared to 23.66% in Phase I against the gold descriptions. In the aspect of sentiment analysis, the generated descriptions cannot effectively capture all sentiment polarities from paragraphs while doing this task better from the gold descriptions. The automatic generation of new descriptions reduces the human efforts in creating them and enriches Wikidata-based knowledge graphs. Our paper shows a practical impact on Wikipedia and Wikidata since there are thousands of missing descriptions. Finally, we expect WikiDes to be a useful dataset for related works in capturing salient information from short paragraphs. The curated dataset is publicly available at: https://github.com/declare-lab/WikiDes.

While the distribution patterns of cold-water corals, such as Paragorgia arborea, have received increasing attention in recent studies, little is known about their in situ activity patterns. In this paper, we examine polyp activity in P. arborea using machine learning techniques to analyze high-resolution time series data and photographs obtained from an autonomous lander cluster deployed in the Stjernsund, Norway. An interactive illustration of the models derived in this paper is provided online as supplementary material. We find that the best predictor of the degree of extension of the coral polyps is current direction with a lag of three hours. Other variables that are not directly associated with water currents, such as temperature and salinity, offer much less information concerning polyp activity. Interestingly, the degree of polyp extension can be predicted more reliably by sampling the laminar flows in the water column above the measurement site than by sampling the more turbulent flows in the direct vicinity of the corals. Our results show that the activity patterns of the P. arborea polyps are governed by the strong tidal current regime of the Stjernsund. It appears that P. arborea does not react to shorter changes in the ambient current regime but instead adjusts its behavior in accordance with the large-scale pattern of the tidal cycle itself in order to optimize nutrient uptake.

In a grid with a significant share of renewable generation, operators will need additional tools to evaluate the operational risk due to the increased volatility in load and generation. The computational requirements of the forward uncertainty propagation problem, which must solve numerous security-constrained economic dispatch (SCED) optimizations, is a major barrier for such real-time risk assessment. This paper proposes a Just-In-Time Risk Assessment Learning Framework (JITRALF) as an alternative. JITRALF trains risk surrogates, one for each hour in the day, using Machine Learning (ML) to predict the quantities needed to estimate risk, without explicitly solving the SCED problem. This significantly reduces the computational burden of the forward uncertainty propagation and allows for fast, real-time risk estimation. The paper also proposes a novel, asymmetric loss function and shows that models trained using the asymmetric loss perform better than those using symmetric loss functions. JITRALF is evaluated on the French transmission system for assessing the risk of insufficient operating reserves, the risk of load shedding, and the expected operating cost.

This study develops a framework for unmanned aerial systems (UASs) to monitor fall hazard prevention systems near unprotected edges and openings in high-rise building projects. A three-step machine-learning-based framework was developed and tested to detect guardrail posts from the images captured by UAS. First, a guardrail detector was trained to localize the candidate locations of posts supporting the guardrail. Since images were used in this process collected from an actual job site, several false detections were identified. Therefore, additional constraints were introduced in the following steps to filter out false detections. Second, the research team applied a horizontal line detector to the image to properly detect floors and remove the detections that were not close to the floors. Finally, since the guardrail posts are installed with approximately normal distribution between each post, the space between them was estimated and used to find the most likely distance between the two posts. The research team used various combinations of the developed approaches to monitor guardrail systems in the captured images from a high-rise building project. Comparing the precision and recall metrics indicated that the cascade classifier achieves better performance with floor detection and guardrail spacing estimation. The research outcomes illustrate that the proposed guardrail recognition system can improve the assessment of guardrails and facilitate the safety engineer's task of identifying fall hazards in high-rise building projects.

We introduce VISOR, a new dataset of pixel annotations and a benchmark suite for segmenting hands and active objects in egocentric video. VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets. Specifically, we need to ensure both short- and long-term consistency of pixel-level annotations as objects undergo transformative interactions, e.g. an onion is peeled, diced and cooked - where we aim to obtain accurate pixel-level annotations of the peel, onion pieces, chopping board, knife, pan, as well as the acting hands. VISOR introduces an annotation pipeline, AI-powered in parts, for scalability and quality. In total, we publicly release 272K manual semantic masks of 257 object classes, 9.9M interpolated dense masks, 67K hand-object relations, covering 36 hours of 179 untrimmed videos. Along with the annotations, we introduce three challenges in video object segmentation, interaction understanding and long-term reasoning. For data, code and leaderboards: http://epic-kitchens.github.io/VISOR