A set of rules or steps to solve a problem.

A computing system inspired by the human brain's network of neurons.

A subfield of AI focused on algorithms inspired by the structure and function of the brain.

Teaching computers to learn from and make decisions based on data.

A type of machine learning where the model is trained using labeled data.

A type of machine learning where the model learns from unlabeled data.

Machine learning where an agent learns by interacting with an environment and receiving feedback.

Prejudice in data or model predictions.

A tool that predicts the category of a given input.

Statistical method predicting a continuous value.

Data used to train machine learning models.

Data used to evaluate the performance of machine learning models.

When a model is too closely adapted to the training data and performs poorly on new data.

When a model is too simple to capture underlying trends in the data.

An individual measurable property of something being observed.

The 'answer' or 'result' for a piece of data in supervised learning.

One complete forward and backward pass of all training samples in machine learning.

A subset of the dataset used in one iteration of training.

The step size taken during optimization to adjust model parameters.

A measure of how well a model's predictions match the true values.

A function that determines the output of a neuron in a neural network.

A single layer neural network.

A method for training neural networks by adjusting weights based on the error of predictions.

An optimization technique to minimize the loss by adjusting model parameters.

A multi-dimensional array used in many machine learning frameworks.

A type of deep learning model especially effective for tasks like image recognition.

A type of neural network well-suited for sequential data.

Using a pre-trained model on a new, similar task.

A field of AI that focuses on the interaction between computers and humans through natural language.

A software application designed to simulate human conversation.

The branch of AI and engineering focused on creating robots.

A machine with the ability to apply intelligence to any problem, rather than just one specific problem.

A flowchart-like tree structure used in decision making.

An ensemble learning method that creates a 'forest' of decision trees.

A supervised machine learning model used for classification and regression analysis.

Graph-based structures that store information and the relationships between them.

Using a trained model to make predictions on new data.

Collective behavior of decentralized systems, often inspired by nature.

Grouping a set of objects so that objects in the same group are more similar to each other.

Technique to reduce the number of input variables in a dataset.

A method to simplify the complexity in high-dimensional data.

Models that convert sequences from one domain into sequences in another domain.

A probabilistic model representing variables and their dependencies.

Processes that automatically select the best model for a given dataset and problem.

Optimization algorithms based on the principles of natural evolution.

Simple, efficient rules or methods used to solve complex problems.

A technique to represent words in vectors such that semantically similar words are close in the vector space.

Determining the emotional tone or intent behind a series of words.

Breaking text into individual words or phrases.

Common words (like 'and', 'the') often removed during text processing.

Reducing words to their base or dictionary form.

Reducing words to their root form, which may not always be a valid word.

Identifying and categorizing named entities in text.

Technique where a small model is trained to mimic a larger model.

Training a model to handle tasks it has never seen during training.

Training a model on a very small dataset.

Using unlabeled data to supervise its own training.

Neural networks that aim to recognize patterns in data in a way that's equivariant to transformations.

Computation using quantum-mechanical phenomena.

Technique used in robotics to map an environment.

Finding patterns in data that don't conform to expected behavior.

Replacing missing data with substituted values.

Analyzing time-ordered data points.

A class of AI algorithms.

Network of physical devices.

Processing data closer to the source.

Feedback in reinforcement learning.

Entity in reinforcement learning.

External system in reinforcement learning.

Model-free reinforcement learning algorithm.

Strategy in reinforcement learning.

Dilemma in reinforcement learning.

Modeling decision-making.

Statistical method.

Updating estimates in reinforcement learning.

Combining deep learning and reinforcement learning.

Search algorithm.

Neural networks with shortcuts.

Teaching models to learn.

Scaling inputs in neural networks.

Focusing mechanism in neural networks.

Preventing overfitting in neural networks.

Normalizing activations in a neural network.

Adjusting a model to improve performance.