Related papers: Why Task-Based Training is Superior to Traditional…
As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…
Reinforcement learning practitioners often avoid hierarchical policies, especially in image-based observation spaces. Typically, the single-task performance improvement over flat-policy counterparts does not justify the additional…
[Spreadsheet] Models are invaluable tools for strategic planning. Models help key decision makers develop a shared conceptual understanding of complex decisions, identify sensitivity factors and test management scenarios. Different…
Learnersourcing is a common task in modern computing classrooms, where it is used, for example, for the creation of educational resources such as multiple-choice questions and programming exercises. One less studied type of learnersourced…
A number of automated techniques and tools were proposed in the research literature over the years which aim to support the spreadsheet developer in the process of testing and debugging a faulty spreadsheet. One underlying assumption of…
Multiple supervised learning scenarios are composed by a sequence of classification tasks. For instance, multi-task learning and continual learning aim to learn a sequence of tasks that is either fixed or grows over time. Existing…
A huge amount of data is everyday managed in large organizations in many critical business sectors with the support of spreadsheet applications. The process of elaborating spreadsheet data is often performed in a distributed, collaborative…
As artificial intelligence (AI) systems become ubiquitous in professional contexts, there is an urgent need to equip workers, often with backgrounds outside of STEM, with the skills to use these tools effectively as well as responsibly,…
Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and preferences. Prior works on reward learning have mainly…
Spreadsheets (sometimes also called Excel programs) are powerful tools which play a business-critical role in many organizations. However, due to faulty spreadsheets many bad decisions have been taken in recent years. Since then, a number…
Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model…
The present paper reports the results of testing first year students of Informatics on their algorithmic skills and knowledge transfer abilities in spreadsheet environments. The selection of students plays a crucial role in the project. On…
Moving away from repetitive tasks, robots nowadays demand versatile skills that adapt to different situations. Task-parameterized learning improves the generalization of motion policies by encoding relevant contextual information in the…
This paper discusses the risks and potential impacts of spreadsheet errors in scientific research data in a Neuroscience research centre in the UK. Spreadsheets usage in neuroscience, or indeed any medical discipline, is a largely…
In classification problems, models must predict a class label based on the input data features. However, class labels are organized hierarchically in many datasets. While a classification task is often defined at a specific level of this…
The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks. However, a relatively less discussed topic is what if more context…
It is now widely accepted that errors in spreadsheets are both common and potentially dangerous. Further research has taken place to investigate how frequently these errors occur, what impact they have, how the risk of spreadsheet errors…
Large-scale general domain pretraining followed by downstream-specific finetuning has become a predominant paradigm in machine learning. However, discrepancies between the pretraining and target domains can still lead to performance…
Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge…
Although the pre-training followed by fine-tuning paradigm is used extensively in many fields, there is still some controversy surrounding the impact of pre-training on the fine-tuning process. Currently, experimental findings based on text…