The Machine Learning Glossary

Every definition in machine learning, deep learning, computer vision, and NLP

Annotation

Annotation

Annotation means any extra information that is attached to the data.
Artificial Neural Network

Artificial Neural Network

Artificial Neural Network is an algorithm that works in a similar fashion as the human brain processes and analyzes data.
Augmentation

Augmentation

In data analysis refers to approaches for increasing the amount of data by adding slightly changed copies of current data or creating new synthetic data from an existing dataset.
Backpropagation

Backpropagation

In deep learning, backpropagation is one of the two sub-processes of the training process, which adjust the parameters of the forward propagation with respect to the error it produces.
Bounding Box

Bounding Box

Bounding Box is used in object detection in which the objects are wrapped around an imaginary rectangle.
COCO

COCO

COCO is an image dataset composed of 90 different classes of objects (cars, persons, sports balls, bicycles, dogs, cats, horses e.t.c). The dataset was gathered to solve common object detection problems.
Computer Vision

Computer Vision

Computer Vision is a field of Artificial Intelligence that focuses on developing techniques that help computers see and understand the content of digital images.
Convolutional Neural Networks

Convolutional Neural Networks

Convolutional Neural Networks also known as ConvNets are a type of Feed-Forward Neural networks used in tasks like image analysis, natural language processing, or other complex image classification problems.
Dataset

Dataset

Dataset is a collection of meaningful data which the machine sees and learns.
Deep Learning

Deep Learning

Deep Learning is a sub-field of machine learning that works in a manner inspired by the neurons of the brain.
Ensemble learning

Ensemble learning

Ensemble Learning is a method of reaching a consensus in predictions by fusing the salient properties of two or more models.
Feedforward Propagation

Feedforward Propagation

In deep learning, feedforward propagation is one of the two sub-processes of the training process, which builds correlation by assigning parameters.
Image Preprocessing

Image Preprocessing

Image Preprocessing are the steps we take to convert a raw image into an enhanced form that the model is ready to use for training and inference.
Image Recognition

Image Recognition

Image recognition is the ability of the machine to identify objects, places, people in an image.
Image Segmentation

Image Segmentation

Image segmentation is a subfield of Artificial Intelligence and Computer Vision typically used to locate objects and boundaries in images.
Instance Segmentation

Instance Segmentation

Instance segmentation models classify pixels into categories on the basis of “instances” rather than classes.
Machine Learning

Machine Learning

Machine Learning is a branch of Artificial Intelligence that allows computers to imitate humans in decision-making without being explicitly programmed.
Natural Language Processing

Natural Language Processing

Natural Language Processing refers to the branch of Artificial Intelligence that gives machines the ability to read, understand and derive meaning from languages, just like humans do.
Neuron

Neuron

Neuron is the basic computational unit of a neural network.
Object Detection

Object Detection

Object detection is a technology that includes computer vision and image processing used to detect objects of a certain class in images or videos.
Object Tracking

Object Tracking

Object tracking is a deep learning process where the algorithm tracks the movement of an object. In other words, it is the task of estimating or predicting the positions and other relevant information of moving objects in a video.
Overfitting

Overfitting

Overfitting refers to the model that models the training data way too well.
Panoptic Segmentation

Panoptic Segmentation

Panoptic segmentation can be expressed as the combination of semantic segmentation and instance segmentation where each instance of an object in the image is segregated and the object’s identity is predicted.
Polygon

Polygon

Polygons are a type of image annotation method, particularly effective thanks to the ability to create a mask around the desired object at a pixel level.
Reinforcement Learning

Reinforcement Learning

Reinforcement Learning is a type of machine learning algorithm that learns to solve a multi-level problem by trial and error.
Semantic Segmentation

Semantic Segmentation

Semantic Segmentation involves a finer approach of labeling each pixel of an image with the class of its enclosing object or region.
Supervised Learning

Supervised Learning

Supervised Learning is the machine learning approach defined by its use of labeled datasets to train algorithms to classify data and predict outcomes.
Test Data

Test Data

Test data is a set of data that is used to test the model after complete training has been done.
Training Data

Training Data

Training Data is a set of data that is fed to any machine learning algorithm for it to learn and derive patterns and use this knowledge for further predictions.
Underfitting

Underfitting

Underfitting occurs when we have a high bias in our data, i.e., we are oversimplifying the problem, and as a result, the model does not work correctly in the training data.
Unsupervised Learning

Unsupervised Learning

Unsupervised Learning is a type of machine learning in which the algorithms are provided with data that does not contain any labels or explicit instructions on what to do with it.
Validation Data

Validation Data

Validation Data is a set of data apart from the training data that is used to validate the model during training.
Label your own datasets on V7
Try our trial or talk to one of our experts.