Definitions

The data science and artificial intelligence
terms you need while reading the latest research

Deep Learning

Deep learning is a machine learning method using multiple layers of nonlinear processing units to extract features from data. Find out more on DeepAI.

Natural Language Processing Machine Learning Computer Vision
05/17/2019 ∙ 111 ∙ share

read it
Adversarial Machine Learning

Adversarial Machine Learning is a collection of techniques to train neural networks on how to spot intentionally misleading data or behaviors.

Vector Machine Learning Defensive Distillation
05/17/2019 ∙ 105 ∙ share

read it
Batch Normalization

Batch Normalization is a supervised learning technique that converts selected inputs in a neural network layer into a standard format, called normalizing.

Supervised Learning Deep Learning Loss Function
05/17/2019 ∙ 100 ∙ share

read it
Convolutional Neural Networks

A convolutional neural network is a type of neural network that is most commonly applied to processing and analyzing visual imagery.

Neural Network Natural Language Processing Artificial Intelligence
05/17/2019 ∙ 93 ∙ share

read it
Neural Network

What is a neural network, and how is it related to machine learning and artificial intelligence?

Machine Learning Classifier Neurons
05/17/2019 ∙ 88 ∙ share

read it
Autoencoder

An autoencoder is an unsupervised learning technique for neural networks that learns efficient data representations (encoding) by training the network to ignore signal “noise.”

Unsupervised Learning Denoising Autoencoders Contractive Autoencoder
05/17/2019 ∙ 82 ∙ share

read it
Feature Extraction

Feature extraction is a process by which an initial set of data is reduced by identifying key features of the data for machine learning.

Machine Learning Natural Language Processing Unsupervised Learning
05/17/2019 ∙ 79 ∙ share

read it
Deep Belief Network

Deep Belief Networks (DBNs) are a laddering of individual unsupervised networks that use each network’s hidden layer as the input for the next layer.

Supervised Learning Unsupervised Learning Restricted Boltzmann Machine
05/17/2019 ∙ 78 ∙ share

read it
Principle of Maximum Entropy

The principle of maximum entropy requires selecting the most unpredictable (maximum entropy) prior probability if only a single parameter is known about a probability distribution.

Prior Probability Geometric Distribution Exponential Distribution
05/17/2019 ∙ 78 ∙ share

read it
Bayesian Networks

Bayesian networks are graphical models that use Bayesian inference to represent variables and their conditional dependencies.

Random Variable Bayesian Inference Probability Distribution
05/17/2019 ∙ 76 ∙ share

read it
Tensor

A Tensor is a mathematical object similar to, but more general than, a vector and often represented by an array of components that describe functions relevant to coordinates of a space. Put simply, a Tensor is an array of numbers that transform according to certain rules under a change of coordinates.

Neural Network Vector Machine Learning
05/17/2019 ∙ 76 ∙ share

read it