Related papers: Why Task-Based Training is Superior to Traditional…

Spreadsheets offer a supremely successful and intuitive means of processing and exchanging numerical content. Its intuitive ad-hoc nature makes it hugely popular for use in diverse areas including business and engineering, yet these very…

Testing the implementation of deep learning systems and their training routines is crucial to maintain a reliable code base. Modern software development employs processes, such as Continuous Integration, in which changes to the software are…

Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due…

Edge computing is the natural progression from Cloud computing, where, instead of collecting all data and processing it centrally, like in a cloud computing environment, we distribute the computing power and try to do as much processing as…

Spreadsheets are used extensively within today's organisations. Although spreadsheets have many benefits, they can also present a significant risk exposure, requiring appropriate management. Protiviti has worked with a number of…

Spreadsheet tables are often labeled, and these labels effectively constitute types for the data in the table. In such cases tables can be considered to be built from typed data where the placement of values within the table is controlled…

This paper describes a framework for a systematic classification of spreadsheet errors. This classification or taxonomy of errors is aimed at facilitating analysis and comprehension of the different types of spreadsheet errors. The taxonomy…

Research on spreadsheet errors is substantial, compelling, and unanimous. It has three simple conclusions. The first is that spreadsheet errors are rare on a per-cell basis, but in large programs, at least one incorrect bottom-line value is…

Episodic training is a mainstream training strategy for few-shot learning. In few-shot scenarios, however, this strategy is often inferior to some non-episodic training strategy, e. g., Neighbourhood Component Analysis (NCA), which…

The hard coding of input data or constants into spreadsheet formulas is widely recognised as poor spreadsheet model design. However, the importance of avoiding such practice appears to be underestimated perhaps in light of the lack of…

Current prescriptions for spreadsheet style specify modular separation of data, calcu1ation and output, based on the notion that writing a spreadsheet is like writing a computer program. Instead of a computer programming style, this article…

Legacy spreadsheets are both, an asset, and an enduring problem concerning spreadsheets in business. To make spreadsheets stay alive and remain correct, comprehension of a given spreadsheet is highly important. Visualization techniques…

In this paper, we discuss the problem of the software engineering of a class of business spreadsheet models. A methodology for structured software development is proposed, which is based on structured analysis of data, represented as…

Meta-learning has emerged as an effective methodology to model several real-world tasks and problems due to its extraordinary effectiveness in the low-data regime. There are many scenarios ranging from the classification of rare diseases to…

Visualizations of tabular data are widely used; understanding their effectiveness in different task and data contexts is fundamental to scaling their impact. However, little is known about how basic tabular data visualizations perform…

Fine-tuning of pre-trained deep nets is commonly used to improve accuracies and training times for neural nets. It is generally assumed that pre-training a net for optimal source task performance best prepares it for fine-tuning to learn an…

The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better…

Pre-training is a widely used approach to develop models that are robust to distribution shifts. However, in practice, its effectiveness varies: fine-tuning a pre-trained model improves robustness significantly in some cases but not at all…

Research on formulae production in spreadsheets has established the practice as high risk yet unrecognised as such by industry. There are numerous software applications that are designed to audit formulae and find errors. However these are…

The use of uncontrolled financial spreadsheets can expose organizations to unacceptable business and compliance risks, including errors in the financial reporting process, spreadsheet misuse and fraud, or even significant operational…