English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Background: We are witnessing an increasing adoption of machine learning(ML), especially deep learning (DL) algorithms in many software systems,including safety-critical systems such as health care systems or autonomousdriving vehicles. Ensuring the software quality of these systems is yet an openchallenge for the research community, mainly due to the inductive nature of MLsoftware systems. Traditionally, software systems were constructed deductively,by writing down the rules that govern the behavior of the system as programcode. However, for ML software, these rules are inferred from training data.Few recent research advances in the quality assurance of ML systems haveadapted different concepts from traditional software testing, such as mutationtesting, to help improve the reliability of ML software systems. However, it isunclear if any of these proposed testing techniques from research are adoptedin practice. There is little empirical evidence about the testing strategies ofML engineers. Aims: To fill this gap, we perform the first fine-grainedempirical study on ML testing practices in the wild, to identify the MLproperties being tested, the followed testing strategies, and theirimplementation throughout the ML workflow. Method: First, we systematicallysummarized the different testing strategies (e.g., Oracle Approximation), thetested ML properties (e.g., Correctness, Bias, and Fairness), and the testingmethods (e.g., Unit test) from the literature. Then, we conducted a study tounderstand the practices of testing ML software. Results: In our findings: 1)we identified four (4) major categories of testing strategy including Grey-box,White-box, Black-box, and Heuristic-based techniques that are used by the MLengineers to find software bugs. 2) We identified 16 ML properties that aretested in the ML workflow.

Studying the Practices of Testing Machine Learning Software in the Wild