Related papers: Why Task-Based Training is Superior to Traditional…
Human beings can leverage knowledge from relative tasks to improve learning on a primary task. Similarly, multi-task learning methods suggest using auxiliary tasks to enhance a neural network's performance on a specific primary task.…
Testing is a vital part of software development, and spreadsheets are like any other software in this respect. This paper discusses the testing of spreadsheets in the light of one practitioner's experience. It considers the concept of…
Spreadsheets offer a supremely successful democratisation platform, placing the manipulation and presentation of numbers within the grasp of users that have little or no mathematical expertise or IT experience. What appears to be almost…
Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not…
Research on spreadsheet errors began over fifteen years ago. During that time, there has been ample evidence demonstrating that spreadsheet errors are common and nontrivial. Quite simply, spreadsheet error rates are comparable to error…
The ability to accurately estimate job runtime properties allows a scheduler to effectively schedule jobs. State-of-the-art online cluster job schedulers use history-based learning, which uses past job execution information to estimate the…
A new MS Excel application has been developed which seeks to reduce the risks associated with the development, operation and auditing of Excel spreadsheets. FormulaDataSleuth provides a means of checking spreadsheet formulas and data as…
Spreadsheets are widely recognized as the most popular end-user programming tools, which blend the power of formula-based computation, with an intuitive table-based interface. Today, spreadsheets are used by billions of users to manipulate…
Tables store rich numerical data, but numerical reasoning over tables is still a challenge. In this paper, we find that the spreadsheet formula, which performs calculations on numerical values in tables, is naturally a strong supervision of…
The benefit of multi-task learning over single-task learning relies on the ability to use relations across tasks to improve performance on any single task. While sharing representations is an important mechanism to share information across…
Spreadsheet engineering methodologies are diverse and sometimes contradictory. It is difficult for spreadsheet developers to identify a spreadsheet engineering methodology that is appropriate for their class of spreadsheet, with its unique…
Fifteen years of research studies have concluded unanimously that spreadsheet errors are both common and non-trivial. Now we must seek ways to reduce spreadsheet errors. Several approaches have been suggested, some of which are promising…
In the Mixup training paradigm, a model is trained using convex combinations of data points and their associated labels. Despite seeing very few true data points during training, models trained using Mixup seem to still minimize the…
We propose a research strategy for creating and deploying prescriptive recommendations for spreadsheet practice. Empirical data on usage can be used to create a taxonomy of spreadsheet classes. Within each class, existing practices and…
Recent research has highlighted the high incidence of errors in spreadsheet models used in industry. In an attempt to reduce the incidence of such errors, a teaching approach has been devised which aids students to reduce their likelihood…
This paper offers a brief review of cognitive verbs typically used in the literature to describe standard spreadsheet practices. The verbs identified are then categorised in terms of Bloom's Taxonomy of Hierarchical Levels, and then rated…
The traditional approach to spreadsheet auditing generally consists of auditing every distinct formula within a spreadsheet. Although tools are developed to support auditors during this process, the approach is still very time consuming and…
Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs, and various other document types, a flurry of table pre-training frameworks have been proposed following the success of text and images, and they have…
Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of…
Developing an error-free spreadsheet has been a problem since the beginning of end-user computing. In this paper, we present a methodology that separates the modeling from the implementation. Using proven techniques from Information Systems…