Terminology

webAI Terminology

Canvas

Canvas is the main work space of Navigator. This is the creation area to train, test, and prototype your AI models.

Drawer

The drawer is where the library of Elements are stored.

Element

Elements are the building blocks for creating with Navigator. Elements are a package of code meant to do a function such as train an AI model or show a visual output of a running flow.

Flow

A flow is a series of elements connected together in a particular sequence in order to perform a trained function and provide an output. A basic flow will consist of an input element, AI inference element, and an output element.

Deployment

A deployment gives a user the ability to assign flows to a set of computers and input devices, and decouple a running flow from the Navigator UI allowing the flow to run independently.

Terminology:

Object Detector

An object detector is a computer vision algorithm or model that identifies and localizes specific objects within an image or video. It can detect multiple objects simultaneously by drawing bounding boxes around them.

Classifier

A classifier is an algorithm or model that categorizes input data into different classes or categories based on predefined criteria or features.

Large Language Model (LLM)

A large language model (LLM) is a powerful artificial intelligence model that is trained on a large amount of text data to generate human-like text responses. LLMs can understand and generate coherent and contextually relevant text, making them useful for various natural language processing tasks.

AI Model Training

AI model training refers to the process of training and optimizing an artificial intelligence model using datasets. During training, the model learns patterns, features, and relationships within the data to make accurate predictions or generate desired outputs.

AI Model Inference

AI model inference is the process of using a trained artificial intelligence model to make predictions or generate outputs based on new, unseen data. Inference typically involves applying the trained model to input data and obtaining the corresponding output or prediction.

Bounding Box

A bounding box is a rectangular region that encloses or bounds an object within an image or video. It is commonly used in object detection tasks to visually represent the location and size of detected objects.

Model Confidence

Model confidence refers to the level of certainty or trustworthiness associated with the predictions or outputs generated by an AI model. It indicates the model's belief in the correctness or accuracy of its predictions.

Model Accuracy

Model accuracy is a measure of how well an AI model performs on a given task. It represents the percentage of correct predictions or outputs compared to the total number of predictions made. Higher accuracy indicates better performance.

Computer Vision

Computer vision is a field of artificial intelligence that focuses on enabling computers to gain a high-level understanding of visual data, such as images and videos. It involves the development of algorithms and models to analyze, interpret, and extract meaningful information from visual inputs.