Natural Language Processing

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.

Generative Adversarial Network

A generative adversarial network (GAN) is an unsupervised machine learning architecture that trains two neural networks by forcing them to “outwit” each other.

Evaluation Metrics

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

Convolutional Neural Network

A convolutional neural network, or CNN, is a deep learning neural network designed for processing structured arrays of data such as images.

Batch Normalization

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

Attention Models

Attention models break down complicated tasks into smaller areas of attention that are processed sequentially.

Bayes Theorem

Bayes’ theorem is a formula that governs how to assign a subjective degree of belief to a hypothesis and rationally update that probability with new evidence. Mathematically, it's the the likelihood of event B occurring given that A is true.

Posterior Probability

In statistics, the posterior probability expresses how likely a hypothesis is given a particular set of data.

F-Score

The F score, also called the F1 score or F measure, is a measure of a test’s accuracy.

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.

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.

Disentangled Representation Learning

Disentangled representation is an unsupervised learning technique that breaks down, or disentangles, each feature into separate, lower dimension variables.

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.

Anomaly Detection

Anomaly Detection (Machine Learning)

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.

Gated Neural Network

In short, a Gated Neural Network (GNN) allows for the layers of the network to learn in increments, rather than creating transformations from scratch. The gate in the neural network is used to decide whether the network can use the shortened identity connections, or if it will need to use the stacked layers.

Statistical Learning Theory

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

High-Dimensional Statistics

What are High-Dimensional Statistics?

Mathematical Optimization

Mathematical optimization is the process of maximizing or minimizing an objective function by finding the best available values across a set of inputs.

Type I error

A Type I error is a false positive in a test outcome where something is falsely inferred to exist.

Markov Model

In short, the Markov Model is the prediction of an outcome is based solely on the information provided by the current state, not on the sequence of events that occurred before.