Purpose: Regular fields are used to capture and annotate various types of information associated with a data point.
Examples: Regular fields can include information such as text, numbers, dates, or any other relevant data that needs to be annotated.
Use Cases: Regular fields are suitable for tasks where the model needs to learn from multiple aspects of the data, not necessarily classifying into predefined categories.
Classification Fields:
Purpose: Classification fields are specifically designed for tasks that involve categorizing data points into predefined classes or categories.
Examples: Classification fields are typically used for tasks like image classification, sentiment analysis, or any other task where the goal is to assign data points to specific classes.
Use Cases: Classification fields are particularly useful when the machine learning model needs to be trained to recognize and classify data into distinct categories.
Classification fields define the categories or classes that your machine learning model will predict. Each instance of labeled data is associated with a classification field indicating its category.
In document processing scenarios, classification is used to know what type document is real is, suppose we are processing 3 doc invoice, bill , receipt human can classify but how can machine classify so models in UiPath already train by that they can understand which is bill , receipt or invoice
In image recognition, based on deep learning they might represent object categories and recognize car , people , tree etc
by