Related papers: Why Task-Based Training is Superior to Traditional…
We present a widely-used operations management model used in supply and distribution planning, that is typically embedded in a periodic business process that necessitates model modification and reuse. We consider three alternative…
The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model. This workload-driven approach, however, has two major…
He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional…
Spreadsheets are widely used, and studies have shown that most end-user spreadsheets contain nontrivial errors. To improve end-users productivity, recent research proposes the use of a model-driven engineering approach to spreadsheets. In…
Students learning how to apply spreadsheets to accounting problems are not always well served by the built-in financial functions. Problems can arise because of differences between UK and US practice, through anomalies in the functions…
There have been many articles and mishaps published about the risks of uncontrolled spreadsheets in today's business environment, including non-compliance, operational risk, errors, and fraud all leading to significant loss events.…
Spreadsheet tools are widely accessible to and commonly used by K-12 students and teachers. They have an important role in data collection and organization. Beyond data organization, spreadsheets also make data visible and easy to interact…
Despite strong evidence of widespread errors, spreadsheet developers rarely subject their spreadsheets to post-development testing to reduce errors. This may be because spreadsheet developers are overconfident in the accuracy of their…
Most spreadsheet surveys both for reporting use and error focus on the practical application of the spreadsheet in a particular industry. Typically these studies will illustrate that a particular percentage of spreadsheets are used for…
Accuracy in spreadsheet modelling systems can be reduced due to difficulties with the inputs, the model itself, or the spreadsheet implementation of the model. When the "true" outputs from the system are unknowable, accuracy is evaluated…
Instruction tuning has been proven effective in enhancing zero-shot generalization across various tasks and in improving the performance of specific tasks. For task-specific improvements, strategically selecting and training on related…
Spreadsheets are widely used in industry, even for critical business processes. This implies the need for proper risk assessment in spreadsheets to evaluate the reliability and validity of the spreadsheet's outcome. As related research has…
Multi-task learning (MTL) aims to leverage shared information among tasks to improve learning efficiency and accuracy. However, MTL often struggles to effectively manage positive and negative transfer between tasks, which can hinder…
Modern spreadsheet systems can be used to implement complex spreadsheet applications including data sheets, customized user forms and executable procedures written in a scripting language. These applications are often developed by…
Errors in spreadsheet applications and models are alarmingly common (some authorities, with justification cite spreadsheets containing errors as the norm rather than the exception). Faced with this body of evidence, the auditor can be faced…
The paper presents two complementary strategies for identifying errors in spreadsheet programs. The strategies presented are grounded on the assumption that spreadsheets are software, albeit of a different nature than conventional…
Diverse studies in systems neuroscience begin with extended periods of curriculum training known as `shaping' procedures. These involve progressively studying component parts of more complex tasks, and can make the difference between…
Meta-learning is a popular framework for learning with limited data in which an algorithm is produced by training over multiple few-shot learning tasks. For classification problems, these tasks are typically constructed by sampling a small…
Table Question-Answering involves both understanding the natural language query and grounding it in the context of the input table to extract the relevant information. In this context, many methods have highlighted the benefits of…
This paper presents the results of an empirical evaluation of the quality of a structured methodology for the development of spreadsheet models, proposed in numerous previous papers by Rajalingham K, Knight B and Chadwick D et al. This…