Definitions

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

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 ∙ 281 ∙ share

read it
Evaluation Metrics

Evaluation metrics are used to measure the quality of the statistical or machine learning model.

Machine Learning Confusion Matrix
05/17/2019 ∙ 219 ∙ share

read it
Natural Language Processing

In simple words, Natural Language Processing is a field which aims to make computer systems understand human speech. NLP is comprised of techniques to process, structure, categorize raw text and extract information.

05/17/2019 ∙ 208 ∙ share

read it
Active Learning

Active learning is a form of semi-supervised machine learning where the algorithm chooses which data to learn from and queries a teacher for guidance.

Natural Language Processing Supervised Learning Machine Learning
05/17/2019 ∙ 199 ∙ 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 ∙ 184 ∙ 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 ∙ 183 ∙ share

read it
Statistical Learning Theory

Statistical learning theory is the broad framework for studying the concept of inference in both supervised and unsupervised machine learning.

Probability Machine Learning Deep Learning
05/17/2019 ∙ 177 ∙ share

read it
Feature Selection

Feature selection is the process by which a subset of features, or variables, are selected from a large dataset for building machine learning models.

Machine Learning Natural Language Processing Feature reduction
05/17/2019 ∙ 177 ∙ 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 ∙ 175 ∙ 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 ∙ 175 ∙ share

read it
Hidden Markov Model

Hidden Markov Model is a statistical Markov model in which the model states are hidden.

Probability Markov Model Probability Distribution
05/17/2019 ∙ 166 ∙ share

read it

Drive top data science
& engineering talent
to openings at your organization