What does the following expression do?

subTotalAdditions.Select(Function(field) CDec(documentFields(field))).ToList.Sum() + subtotal

A. Sums up subtotal fields from the config file converted to CDec with the subtotal.

B. Sums up all the line amounts and converts the fields to CDec.

C. Sums up all the line amounts converted to CDec and the subtotal.

D. Sums up the subtotal to the total variable by converting it to CDec.

What is the purpose of the End Process in the Document Understanding Process?

A. The purpose of the End Process in the Document Understanding Process is to generate a summary report of the processing statistics and performance metrics.

B. End Process sets the queue transaction status as Successful in case of no exception, and as Failed in case of an exception with their corresponding Business or System Exception, and the post processing/cleaning if required.

C. End Process in the Document Understanding Process silently shuts down the Virtual Machine so that another robot can use it.

D. End Process is a feature in the Document Understanding Process that exports the extracted data into a readable document format.

When dealing with variable-length data, or data spanning over multiple pages of the document (e.g. item tables), what is the recommended data extraction methodology to be used?

A. Hybrid data extraction.

B. Rule-based data extraction.

C. Model-based data extraction.

D. Manual data extraction.

Which activity should be used for classification validation in attended mode?

A. Create Document Classification Action.

B. Train Classifiers Scope.

C. Wait for Document Classification and Resume.

D. Present Classification Station.

What happens during the Classify stage of the Document Understanding Framework?

A. The OCR engine is used to extract text from the image document.

B. The extracted data is exported as a dataset.

C. The target fields are extracted from the document and sent to Action Center for human validation.

D. The documents are included in one of the taxonomy document types or skipped.

Which are all the options for managing ML Skills?

A. ML skills can be created, stopped, redeployed, updated to a new package version, rolled back to a previous package version, modified to use or not use GPU, made public or private, or deleted.

B. ML skills can be created, stopped, redeployed, updated to a new package version, rolled back to a previous package version, made public or private, or deleted.

C. ML skills can be created, stopped, redeployed, updated to a new package version, rolled back to a previous package version, modified to use or not use GPU, modified to use or not use AI units, made public or private, or deleted.

D. ML skills can be created, updated to a new package version, rolled back to a previous package version, modified to use or not use GPU, made public or private, or deleted.

What additional property does the ML Extractor have compared to the other types of extractors?

A. Endpoint.

B. ML Skill.

C. Timeout.

D. ApiKey.

What is unsupervised learning?

A. Unsupervised learning is a machine learning paradigm in which algorithms try to solve a problem only by trial and error and using a system of rewards and punishments. There is no need for labeled input/output pairs to be presented. Instead, the focus is on finding a balance between exploration (of uncharted territory) and exploitation (of current knowledge).

B. Unsupervised learning is a machine learning paradigm that refers to algorithms that learn patterns from unlabeled data. There are only input variables, but no corresponding output variables. The goal of the algorithm is to model the underlying structure of the data, but there are no correct answers and no teachers.

C. Unsupervised learning is a machine learning paradigm with the goal of learning a function that maps input variables with output variables. In every case there is a correct answer, so the aim is to train the model until it reaches an acceptable level of performance in predicting the outcome, at which point the learning stops.

D. Unsupervised learning is a machine learning paradigm in which algorithms try to solve a problem in an uncertain, potentially complex environment only by trial and error and using a system of rewards and punishments. There are no correct answers, but feedback is given in the form of rewards and penalties.

What type of data extraction methodology should be used, according to best practices, for a fixed layout document (e.g. a form)?

A. Model-based data extraction.

B. Hybrid data extraction.

C. Manual data extraction.

D. Rule-based data extraction.

In the context of Post Processing, how do you modify the value of countryField to Taiwan in the io_ExtractionResult object?

addressField = io_ExtractionResults.ResultsDocument.Fields.Where(Function(field) field.FieldType.Equals(UiPath.DocumentProcessing.Contracts.Taxonomy.FieldType.Address)).FirstOrDefault

countryField = io_ExtractionResults.ResultsDocument.Fields.Where(Function(field) field.FieldName.Equals("Country")).FirstOrDefault

A. countryField.Value = Taiwan

B. countryField.Values(0).Value = Taiwan

C. countryField.Values(0) = Taiwan

D. countryField.Fields(0).Value = Taiwan