AI Glossary

Definition: A step-by-step procedure for solving a problem or accomplishing a task.
Example: The k-means clustering algorithm partitions data points into distinct groups based on their features.

Definition: The simulation of human intelligence by machines.
Example: Virtual assistants like Siri and Alexa use AI to respond to user commands.

Definition: An algorithm for training neural networks by adjusting weights based on error rates.
Example: Backpropagation is used to improve the accuracy of image recognition models.

Definition: Extremely large datasets that can be analyzed to reveal patterns and trends.
Example: Social media platforms analyze big data to identify user behavior patterns.

Definition: A program designed to simulate conversation with human users.
Example: Customer service chatbots on websites assist users with queries.
Example: Social media platforms analyze big data to identify user behavior patterns.

Definition: A machine learning task of categorizing data into predefined classes.
Example: Email spam filters classify emails as "spam" or "not spam".

Definition: The process of grouping a set of objects into clusters based on similarity.
Example: Clustering algorithms can segment customers into distinct groups based on purchasing behavior.
Example: Social media platforms analyze big data to identify user behavior patterns.

Definition: Extremely large datasets that can be analyzed to reveal patterns and trends.
Definition: The process of discovering patterns and knowledge from large amounts of data.
Example: Retail companies use data mining to find buying patterns and increase sales.

Definition: A step-by-step procedure for solving a problem or accomplishing a task.
Definition: The process of cleaning and preparing raw data for analysis.
Example: Removing duplicates and filling missing values in a dataset.

Definition: A subset of machine learning involving neural networks with many layers.
Definition: A tree-like model used to make decisions based on input features.
Example: Decision trees help in diagnosing medical conditions based on symptoms.

Definition: The process of using domain knowledge to create new input features for a machine learning model.
Example: Creating new features from existing data to improve model performance.

Definition: A step-by-step procedure for solving a problem or accomplishing a task.
Definition: The process of transforming raw data into numerical features that can be processed while preserving the information in the original data.
Example: Extracting edges and shapes from images for computer vision tasks.

Definition: An optimization technique based on the principles of natural selection and genetics.
Example: Genetic algorithms can optimize complex problems like scheduling and design.

Definition: A step-by-step procedure for solving a problem or accomplishing a task.
Definition: External parameters of a model set before training begins.
Example: Learning rate and number of epochs in a neural network.

Definition: A step-by-step procedure for solving a problem or accomplishing a task.
Definition: A branch of AI that focuses on building systems that learn from and make decisions based on data.
Example: Recommendation systems on streaming platforms use machine learning to suggest content.

Definition: The process of teaching a machine learning model to make predictions or decisions based on data.
Example: Training a model to predict house prices based on historical data.

Definition: The field of AI that focuses on the interaction between computers and humans using natural language.
Example: Sentiment analysis of social media posts.

Definition: A computational model inspired by the human brain, consisting of interconnected nodes (neurons).
Example: Convolutional neural networks are used in image recognition tasks.
Example: The k-means clustering algorithm partitions data points into distinct groups based on their features.

Definition: When a model learns the training data too well, including noise and outliers, resulting in poor generalization to new data.
Example: A model that performs well on training data but poorly on test data.
Example: The k-means clustering algorithm partitions data points into distinct groups based on their features.

Definition: The process of creating, testing, and validating a model to predict future outcomes based on historical data.
Example: Predicting stock prices using historical market data.

Definition: A type of machine learning where an agent learns to make decisions by taking actions in an environment to maximize cumulative reward.
Example: Training an AI to play chess by rewarding wins and penalizing losses.

Definition: A type of predictive modeling technique that estimates the relationships among variables.
Example: Linear regression can predict a person's weight based on their height and age.

Definition: The field of engineering and science that involves the design, construction, and operation of robots.
Example: Autonomous robots used in manufacturing.

Definition: A type of machine learning where the model is trained on labeled data.
Example: Classifying emails as spam or not spam using a labeled dataset.

Definition: A supervised learning algorithm used for classification and regression tasks.
Example: SVMs can classify images into different categories.

Definition: An open-source software library for dataflow and differentiable programming across a range of tasks.
Example: TensorFlow is widely used for implementing deep learning models.

Definition: The analysis of time-ordered data to extract meaningful statistics and identify trends.
Example: Forecasting stock prices or weather conditions.

Definition: A machine learning technique where a pre-trained model is adapted to a new, but related, problem.
Example: Using a pre-trained image recognition model to identify specific objects in new images.

Definition: A type of machine learning where the model is trained on unlabeled data.
Example: Clustering customers based on purchasing behavior without predefined labels.

Definition: A set of data used to tune the hyperparameters of a model.
Example: Splitting the data into training, validation, and test sets to optimize the model.

Definition: A measure of how much the predictions of a model vary with different training data.
Example: High variance in a model indicates that it may overfit the training data.

Definition: An array of numbers that represents features or attributes of data in machine learning.
Example: Word embeddings in NLP are vectors representing words in a continuous vector space.

Definition: A simple, instance-based learning algorithm used for classification and regression.
Example: KNN can classify a new data point based on the majority class of its nearest neighbors.

​Definition: A technique for assessing how a model will generalize to an independent dataset.
Example: Using k-fold cross-validation to evaluate the performance of a machine learning model.

Definition: A deep learning algorithm primarily used for image processing tasks.
Example: CNNs are used in facial recognition systems.

Definition: The process of reducing the number of random variables under consideration.
Example: Principal Component Analysis (PCA) is used to reduce the dimensionality of large datasets.

Definition: An optimization algorithm used to minimize the loss function in machine learning models.
Example: Gradient descent is used to update the weights in a neural network during training.

Definition: A rule-of-thumb or practical approach to problem-solving that is not guaranteed to be perfect but is sufficient for reaching an immediate goal.
Example: Heuristics are used in search algorithms to find approximate solutions quickly.

Definition: A statistical model used for binary classification tasks.
Example: Predicting whether a user will click on an advertisement (click or no click).
Example: Grid search and random search are common methods for hyperparameter tuning.

Definition: A measure of the average squared difference between predicted and actual values.
Example: MSE is used to evaluate the performance of regression models.

Definition: The process of generating natural language text from structured data.
Example: Generating weather reports from meteorological data.

Definition: An automated process for designing neural network architectures.
Example: NAS can be used to find the optimal neural network architecture for a specific task.

Definition: A process of converting categorical data into a binary vector representation.
Example: Converting categorical labels like "red," "green," and "blue" into binary vectors.

Definition: The ratio of true positive results to the total predicted positives in a classification model.
Example: High precision indicates that the model has a low false positive rate.

Definition: The ratio of true positive results to the total actual positives in a classification model.
Example: High recall indicates that the model has a low false negative rate.

Definition: A type of neural network designed to recognize patterns in sequences of data.
Example: RNNs are used for tasks like language modeling and time series prediction.

Definition: A graphical plot illustrating the diagnostic ability of a binary classifier system.
Example: The ROC curve is used to assess the trade-off between sensitivity and specificity.

Definition: The process of breaking text into individual words or phrases.
Example: Tokenizing a sentence into words for processing in natural language tasks

Definition: The process of optimizing the hyperparameters of a model to improve its performance.
Example: Grid search and random search are common methods for hyperparameter tuning.