Machine Learning Glossary

IDD

IID stands for "independent and identically distributed." It is a term used in statistics and probability theory to describe a scenario where each random variable has the same probability distribution as the others and all are mutually independent.

Image Collection

An "image collection" in machine learning refers to a large set of images that are used to train, test, and validate model performance. These collections, often labeled for supervised learning, provide the necessary data that allows the algorithm to learn the correlations and patterns that exist within the image data to make predictions or classifications.

Image Pre-processing

Image preprocessing is a crucial step in the field of computer vision, machine learning, and artificial intelligence that involves executing a set of operations on an image to enhance its quality or extract some useful information from it before it is processed. This process is critical for obtaining better results during the analysis and manipulation of images, such as in image recognition and machine learning algorithms.

Image Recognition

Image recognition is a subset of computer vision, a field that focuses on training and developing computers to gain a high-level understanding from digital images or videos. In the context of machine learning or deep learning, image recognition is a process which identifies and detects an object or attribute in a digital image or video, it can be a particular feature or the full image itself.

Image Segmentation

Image segmentation is a process in computer vision where a digital image is divided into multiple segments or sets of pixels. The goal of segmentation is to simplify or change the representation of an image into something more meaningful and easier to analyze. It aims to assign a label to every pixel in an image such that pixels with the same label share certain visual characteristics.

ImageNet

ImageNet is a massive dataset of over 15 million labeled high-resolution images across about 22,000 categories. Developed by researchers at Stanford and Princeton, ImageNet is commonly used for machine learning purposes, particularly in object recognition tasks. Information provided by this dataset has been instrumental in the development and advancement of deep learning algorithms.

Inference

Inference is the process by which a trained machine learning model applies its learnt patterns and knowledge to new and unseen data. In other words, it is the application phase where the model uses its training to predict outcomes, classify data, or make decisions based on inputs it has not previously seen.

Information Retrieval

Information retrieval is the science of searching for information in a document, searching for documents themselves, and also searching for metadata that describes data, and for databases of texts, images or sounds. It's closely associated with the development and usage of computer-based storage and retrieval mechanisms.

Instance Segmentation

Instance Segmentation is a subfield of computer vision that involves identifying each individual object of interest within an image and delineating its specific boundaries. It is more granular than semantic segmentation, which labels pixels belonging to the same class with the same color but doesn't differentiate between individual objects of the same class. In instance segmentation, each object, even of the same class, is separately identified and marked.

Intelligent Document Processing (IDP)

Intelligent Document Processing (IDP) is an advanced technological solution that employs capabilities like Machine Learning (ML), Natural Language Processing (NLP) to automatically classify, extract, validate, and direct the information contained within documents. IDP goes beyond the capabilities of traditional document management functionalities to understand the context and derive meaningful insights from unstructured data.