Technology

A neural-network design in which an encoder represents input data and a decoder uses that representation to produce an output.

Ensemble learning combines multiple predictive models to improve accuracy, stability, or uncertainty estimation through methods such as bagging, boosting, voting, and stacking.

An iterative method for estimating statistical model parameters when observations are incomplete or depend on unobserved variables.

Explainable artificial intelligence develops methods for making AI behavior and outputs understandable to people while assessing whether explanations faithfully represent the underlying system.

Feature engineering is the creation, transformation, and selection of data representations used as inputs to machine-learning models.

Feature extraction transforms raw observations into representations suitable for machine learning and other forms of computational analysis.

Feature scaling transforms numerical input variables to comparable ranges or statistical scales, affecting distances, optimization, and regularization in machine learning.

Fine-tuning adapts a pretrained neural network to a task or domain through additional training of selected parameters.

FlashAttention is a family of GPU attention algorithms that reduces memory traffic through tiled computation, accelerating Transformers without sparsifying dense attention.

A foundation model is a broadly trained machine-learning model that can be adapted to many downstream tasks, providing a shared basis for specialized artificial-intelligence systems.

American psychologist who developed the perceptron, an early learning neural network that helped establish the foundations of machine learning.

A Gaussian mixture model represents a probability distribution as a weighted combination of Gaussian components, supporting density estimation and probabilistic clustering.

Gel electrophoresis separates biological molecules in a porous gel using an electric field, enabling analysis of their size, charge, and composition.

Generalization is a machine-learning model’s ability to perform effectively on previously unseen data, rather than merely fitting its training examples.

A generative adversarial network learns to synthesize data through competition between a generator and a discriminator.

Generative artificial intelligence produces text, images, audio, and other content by learning patterns from data.

A generative pre-trained transformer is a transformer-based model trained to predict and generate sequences, forming the basis of the GPT language-model family.

Genome editing comprises technologies that make targeted changes to DNA sequences for biological research, agriculture, biotechnology, and medicine.

Gradient boosting builds predictive models by sequentially adding learners that approximate loss-reducing changes to an existing ensemble.

A graphics processing unit is a parallel processor designed for rendering images and accelerating computationally intensive workloads.

A heat engine converts part of an input of thermal energy into mechanical work, subject to limits imposed by thermodynamics.

IBM is an American multinational technology company whose activities span enterprise software, computing infrastructure, consulting, artificial intelligence, and quantum computing.

Image classification is the computational assignment of one or more category labels to an image according to its visual content.

Image processing comprises methods for transforming, enhancing, restoring, compressing, and analyzing images, primarily through computational operations on digital data.

ImageNet is a large, hierarchically organized image dataset that became a foundational benchmark for visual recognition and deep learning.

In-context learning is a model’s ability to adapt its predictions using examples or instructions in its input, without updating its parameters.

An integrated circuit combines interconnected electronic components on a semiconductor substrate to perform processing, storage, amplification, or control functions.

An internal combustion engine converts fuel energy into mechanical work by burning fuel within its working fluid and using the resulting hot gases to produce motion.

The Internet is a global system of interconnected computer networks. They exchange data using the TCP/IP protocol suite and support services such as the Web and email.

Invention is the creation of a new technical solution, including a device, material, process, or improvement to an existing technology.

Irrigation is the controlled application of water to land to support plant growth when rainfall or stored soil moisture is insufficient.

John McCarthy was an American computer scientist who helped establish artificial intelligence, created Lisp, and pioneered logical approaches to machine reasoning.

A Josephson junction is a superconducting weak link that supports phase-dependent supercurrent and enables precision voltage standards, sensitive magnetometers, and superconducting quantum circuits.

A nonparametric learning algorithm that predicts a sample’s class or numerical value from its nearest labeled examples.

A knowledge base is an organized repository of information designed for human consultation, automated reasoning, or retrieval by software systems.

The study of how computational systems encode knowledge and use it to derive conclusions, explain observations, and guide action.

A large language model is a neural language model trained at scale to process and generate text, often supporting many tasks through a shared model.

A laser generates light through stimulated emission, producing beams whose direction, spectrum, and timing can be controlled for scientific, industrial, and technological applications.

A latent space is a model-defined space of unobserved variables or learned representations used to describe, reconstruct, or generate data.

Layer normalization standardizes neural-network activations within each example, using feature-wise statistics and usually learned scale and bias parameters.

A learning curve plots model performance against training-set size or training progress, helping characterize generalization, data requirements, and optimization behavior.

Life-cycle assessment evaluates the potential environmental impacts of products and services across their life cycles.

A rechargeable battery that stores and releases energy through the reversible movement of lithium ions between electrodes.

A logical qubit is an encoded unit of quantum information whose physical representation enables the detection and correction of specified errors.

Long short-term memory is a gated recurrent neural network architecture designed to learn dependencies across sequences while reducing vanishing-gradient difficulties.

Machine learning studies computational methods that learn from data or experience to make predictions, discover patterns, generate content, or select actions.

Marvin Minsky was an American artificial intelligence pioneer known for neural-network research, frame-based knowledge representation, and the Society of Mind theory.

Missing data imputation replaces unavailable observations with plausible values while accounting for assumptions about missingness and, where required, statistical uncertainty.

Multi-head attention combines parallel attention computations with distinct learned projections to represent multiple relationships within or between sequences.

A multilayer perceptron is a feedforward neural network that learns nonlinear mappings through successive layers of weighted connections and activation functions.

Multimodal learning develops machine-learning systems that relate or combine information from different forms of data, such as text, images, audio, and video.

A family of probabilistic classifiers that applies Bayes’ theorem using the assumption that features are conditionally independent given the class.

Natural language processing studies computational methods for analyzing, interpreting, and generating human language in text and speech.

Neural network inference is the execution of a trained neural network to produce predictions or generated outputs from input data, usually without updating its parameters.

An empirical relationship describing how neural-network performance changes with model size, training data, and computational resources.

Nonmonotonic reasoning allows conclusions drawn from incomplete information to be withdrawn when additional information becomes available.

Object detection identifies individual objects in images or video and estimates their locations, usually through labeled bounding boxes.

One-hot encoding represents each category as a binary vector with exactly one active component, enabling categorical data to be processed numerically.

Open-source software is software distributed with source code and licensing rights that permit use, modification, and redistribution.

An operating system manages computer hardware and resources while providing services, abstractions, and execution environments for applications.