We’re now in the world of AI and deep learning, and this space has lots of new terms to become familiar with. Understanding these terms and how they relate to each other makes it easier to work with Einstein Vision.
Dataset—The training data, which consists of inputs and outputs. Training the dataset creates the model used to make predictions. For an image recognition problem, the image examples you provide train the model on the desired output labels that you want the model to predict. For example, in the Create a Custom Classifier Scenario, you create a model named Beach and Mountain Model from a binary training dataset consisting of two labels: Beaches (images of beach scenes) and Mountains (images of mountain scenes). A non-binary dataset contains three or more labels.
Label—A group of similar data inputs in a dataset that your model is trained to recognize. A label references the output name you want your model to predict. For example, for our Beach and Mountain model, the training data contains images of beaches and that label is “Beaches.” Images of mountains have a label of “Mountains.” The food classifier, which is trained from a multi-label dataset, contains labels like chocolate cake, pasta, macaroons, and so on.
Model—A machine learning construct used to solve a classification problem. Developers design a classification model by creating a dataset and then defining labels and providing positive examples of inputs that belong to these labels. When you train the dataset, the system then determines the commonalities and differences between the various labels to generalize the characteristics that define each label. The model predicts which class a new input falls into based on the predefined classes specified in your training dataset.
Training—The process through which a model is created and learns the classification rules based on a given set of training inputs (dataset).
Prediction—The results that the model returns as to how closely the input matches data in the dataset.
Updated 31 minutes ago