# The AI Glossary

This glossary has been curated by data scientists and machine learning experts like you.

## The Appen Artificial Intelligence Glossary

To help those who are just learning about the nuances of AI, we have developed the below Artificial Intelligence Glossary, a list of words and terms which can help prepare you for when AI starts to become a part your everyday conversations.

More than just robots seeking to terminate or games looking to self-engage in a challenge versus humans, artificial intelligence (AI) is the application of complex programmatic math in which the outcome, combined with high quality training data, becomes the technological advances we see occurring in our everyday lives. From self-driving cars to finding cures for cancer, artificial intelligence applied in the real world is becoming a way of life.

### A

#### A/B Testing

#### Activation Function

#### Active Learning (Active Learning Strategy)

#### Algorithm

#### Annotation

#### Area Under the Curve (AUC)

#### Artificial Intelligence

#### Artificial Neural Networks

#### Association Rule Learning

#### Autoencoder

#### Automated Speech Recognition

### B

#### Backpropagation (Backpropagation Through Time)

#### Batch

#### Bayes’s Theorem

#### Bias (Inductive Bias, Confirmation Bias)

*Inductive Bias*: the set of assumptions that the learner uses when predicting outputs given inputs that have not been encountered yet.

*Confirmation Bias*: the tendency to search for, interpret, favor, and recall information in a way that confirms one’s own beliefs or hypotheses while giving disproportionately less attention to information that contradicts it.

#### Bias-Variance Tradeoff

#### Boosting

#### Bounding Box

### C

#### Chatbot

#### Classification

#### Clustering

#### Cold-Start

#### Collaborative Filtering

#### Computer Vision

#### Confidence Interval

#### Contributor

#### Convolutional Neural Network (CNN)

#### Central Processing Unit (CPU)

#### Cross-Validation (k-fold Cross-Validation, Leave-p-out Cross-Validation)

### D

#### Data (Structured Data, Unstructured Data, Data augmentation)

#### Decision Tree

#### Deep Blue

#### Deep Learning (Deep Reinforcement Learning)

**Feature Selection**.

### E

#### Embedding (Word Embedding)

#### Ensemble Methods

#### Entropy

#### Epoch

### F

#### Feature (Feature Selection, Feature Learning)

#### Feature Learning

#### False Positive

#### False Negative

#### Feed-Forward (Neural) Networks

#### F-Score

### G

#### Garbage In, Garbage Out

#### General Data Protection Regulation (GDPR)

#### Genetic Algorithm

#### Generative Adversarial Networks (GANs)

#### Graphic Processing Unit (GPU)

#### Ground Truth

### H

#### Human-in-the-Loop

**“What is Human-in-the-Loop?“**

#### Hyperparameter (Hyperparameter Tuning)

### I

#### ImageNet

#### Image Recognition

#### Inference

#### Information Retrieval

### L

#### Layer (Hidden Layer)

#### Learning-to-Learn

#### Learning-to-Rank

#### Learning Rate

#### Logit Function

#### Long Short-Term Memory Networks

### M

#### Machine Learning

#### Machine Learning Lifecycle Management

#### Machine Translation

#### Model

#### Monte Carlo

#### Multi-Modal Learning

#### Multi-Task Learning

### N

#### Naive Bayes

#### Named Entity Recognition

#### Natural Language Processing (NLP)

#### Neuron

### O

#### Optical Character Recognition

#### Optimization

#### Overfitting

### P

#### Pattern Recognition

#### Pooling (Max Pooling)

#### Personally Identifiable Information

#### Precision

#### Prediction

#### Preprocessing

#### Pre-trained Model

**Transfer Learning**.

#### Principal Component Analysis

#### Prior

### R

#### Random Forest

#### Recall

#### Rectified Linear Unit

#### Recurrent Neural Networks

#### Regression (Linear Regression, Logistic Regression)

*Linear Regression:*a simple type of regression taking a linear combination of features as an input, and outputting a continuous value.

*Logistic Regression:*a type of regression generating a probability for each possible discrete label value in a classification problem by applying a sigmoid function to a linear prediction.

#### Regressor

#### Regularization

#### Reinforcement Learning

#### Reproducibility (crisis of)

#### Restricted Boltzmann Machines

### S

#### Semi-Supervised Learning

**Supervised Learning**and

**Unsupervised Learning**. Sentiment Analysis

#### Statistical Distribution

#### Supervised Learning

#### Support Vector Machines (SVM)

#### Synthetic Data

### T

#### TensorFlow

#### Time Series (Time Series Data)

#### Testing (Testing Data)

#### Topic Modeling

#### Training Data

**What is Training Data?**