Verification and validation of neural networks: a sampling of research in progress

Taylor, Brian J.; Darrah, Marjorie; Moats, Christina

doi:10.1117/12.487527

Cited by 31 publications

(41 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This methodology theoretically provides the best compromise to get both good learning and correct evaluation of the model. It has been already recommended by other authors in the case of quantitative nonlinear models like ANN, pointing out that the only satisfying method to validate an ANN model was the training-validation-testing approach [93]. Indeed, in the case of ANN, one should understand that the calibration set is used to train the ANN models, and the validation set to determine the best ANN model as a function of adjustable parameters, namely the number of layers and nodes, the learning speed and momentum and the number of iterations.…”

Section: Subsets Of Data and Validationmentioning

confidence: 98%

Good practices in LIBS analysis: Review and advices

Haddad

Canioni

Bousquet

2014

Spectrochimica Acta Part B: Atomic Spectroscopy

274

109

View full text Add to dashboard Cite

International audienceThis paper presents a review on the analytical results obtained by laser-induced breakdown spectroscopy (LIBS). In the first part, results on identification and classification of samples are presented including the risk of misclas-sification, and in the second part, results on concentration measurement based on calibration are accompanied with significant figures of merit including the concept of accuracy. Both univariate and multivariate approaches are discussed with special emphasis on the methodology, the way of presenting the results and the assessment of the methods. Finally, good practices are proposed for both classification and concentration measurement

show abstract

Section: Subsets Of Data and Validationmentioning

confidence: 98%

Good practices in LIBS analysis: Review and advices

Haddad

Canioni

Bousquet

2014

Spectrochimica Acta Part B: Atomic Spectroscopy

274

109

View full text Add to dashboard Cite

show abstract

“…Validation, which is actually part of training, is used for parameter selection to avoid over fitting and to determine the stopping point for the backpropagation algorithm. The testing set is then used to determine the performance of the neural network by computing an error metric (Taylor et al, 2003). This training-validating-testing approach accomplished by the repeated application of the training data, followed by the application of the testing data to determine whether the neural network is acceptable, was used to assess the neural network.…”

Section: A C C E P T E D Accepted Manuscriptmentioning

confidence: 99%

Prediction of global horizontal solar irradiance in Zimbabwe using artificial neural networks

Chiteka

Enweremadu

2016

Journal of Cleaner Production

View full text Add to dashboard Cite

“…They grouped the methods into five traditional V&V technique categories: automated testing and testing data generation methods, run-time monitoring, formal methods, cross validation and visualization. In contrast to [15], our study adopted a thematic analysis approach [53] and identified five themes based on the research goals of the selected studies. We thought it was better to classify the proposed T&V methods of NNs based on their aims rather than on the traditional technique categories since many traditional V&V technique are no longer effective for verifying NNs in many cases.…”

Section: Comparison With Related Work 521 Verification and Validatmentioning

confidence: 99%

Testing and verification of neural-network-based safety-critical control software: A systematic literature review

Zhang

2020

Information and Software Technology

View full text Add to dashboard Cite

Context: Neural Network (NN) algorithms have been successfully adopted in a number of Safety-Critical Cyber-Physical Systems (SCCPSs). Testing and Verification (T&V) of NN-based control software in safety-critical domains are gaining interest and attention from both software engineering and safety engineering researchers and practitioners. Objective: With the increase in studies on the T&V of NN-based control software in safety-critical domains, it is important to systematically review the state-of-the-art T&V methodologies, to classify approaches and tools that are invented, and to identify challenges and gaps for future studies. Method: By searching the six most relevant digital libraries, we retrieved 950 papers on the T&V of NN-based Safety-Critical Control Software (SCCS). Then we filtered the papers based on the predefined inclusion and exclusion criteria and applied snowballing to identify new relevant papers. Results: To reach our result, we selected 83 primary papers published between 2001 and 2018, applied the thematic analysis approach for analyzing the data extracted from the selected papers, presented the classification of approaches, and identified challenges. Conclusion: The approaches were categorized into five high-order themes: assuring robustness of NNs, assuring safety properties of NN-based control software, improving the failure resilience of NNs, measuring and ensuring test completeness, and improving the interpretability of NNs. From the industry perspective, improving the interpretability of NNs is a crucial need in safetycritical applications. We also investigated nine safety integrity properties within four major safety lifecycle phases to investigate the achievement level of T&V goals in IEC 61508-3. Results show that correctness, completeness, freedom from intrinsic faults, and fault tolerance have drawn most attention from the research community. However, little effort has been invested in achieving repeatability; no reviewed study focused on precisely defined testing configuration or on defense against common cause failure.

show abstract

Verification and validation of neural networks: a sampling of research in progress

Cited by 31 publications

References 14 publications

Good practices in LIBS analysis: Review and advices

Good practices in LIBS analysis: Review and advices

Prediction of global horizontal solar irradiance in Zimbabwe using artificial neural networks

Testing and verification of neural-network-based safety-critical control software: A systematic literature review

Contact Info

Product

Resources

About