3,135 articles
Resolution (logic)
Resolution, also known as the resolution principle, is a single rule of inference for proving formulas in conjunctive normal form unsatisfiable, developed by J. A. Robinson in 1965.
Resource-constrained project scheduling
Resource-constrained project scheduling (RCPSP) is the NP-hard operations research problem of scheduling project activities under precedence relations and resource limits to minimize the makespan, first formulated in 1967.
Restricted Boltzmann machine
A restricted Boltzmann machine (RBM) is a generative neural network of stochastic units in two layers, trained by contrastive divergence and used to build deep belief networks.
RetinaNet
RetinaNet is a one-stage object detection model introduced in 2017 by Tsung-Yi Lin and colleagues at Facebook AI Research, known for focal loss, which down-weights easy background examples during training.
Rev-9
The Rev-9 is a fictional Terminator model played by Gabriel Luna in Terminator: Dark Fate (2019), combining a metal endoskeleton with a liquid metal exterior.
Reverse ETL
Reverse ETL (rETL, data activation, operational analytics) syncs modeled data from a data warehouse or lakehouse back out into operational tools like CRMs, marketing platforms, and ad systems, inverting traditional ETL's direction; typically batch, with conflict-resolution and latency limits.
Reverse image search
Reverse image search is a search method that submits an image as the query instead of text, returning matching or similar images and the pages containing them.
Reversible data hiding
Reversible data hiding, also called lossless watermarking, embeds secret data in a cover image so both are recovered exactly, making it useful for medical, military, and forensic imagery.
Reward hacking
Reward hacking, also known as specification gaming, is a reinforcement learning failure in which an AI agent exploits flaws in its reward function and performs worse on the true goal.
Reward learning
Reward learning is a machine learning method that infers a reward function from human preferences, demonstrations, or ratings, and underlies RLHF fine-tuning of instruction-following language models like InstructGPT.
Reward tampering
Reward tampering is an AI agent's inappropriate interference with its own reward process, modifying its reward function or its inputs, treated as a dangerous form of reward hacking.
RGB-D salient object detection
RGB-D salient object detection (RGB-D SOD) is a computer vision task that finds the most prominent objects in a scene using a color image plus a depth map.
RIFE
RIFE (Real-Time Intermediate Flow Estimation) is a neural network algorithm for video frame interpolation that estimates intermediate optical flow directly, 4 to 27 times faster than SuperSlomo and DAIN.
Rigid image registration
Rigid image registration, also called rigid registration, aligns two views of an object using only translation and rotation, commonly applied to medical scans of the same patient.
Rill (software)
Rill (rilldata/rill) is an open-source Apache-2.0 BI-as-code tool by Rill Data with DuckDB embedded by default, live OLAP connectors, Explore and Canvas dashboards, Rill Cloud, and MCP-based AI agent integration.
Ring all-reduce
Ring all-reduce is a collective communication algorithm in which devices in a logical ring combine arrays, such as deep learning gradients, with data per device independent of device count.
RisingWave
RisingWave is an open-source distributed SQL streaming database written in Rust by RisingWave Labs (formerly Singularity Data). PostgreSQL wire-compatible, Apache 2.0, Hummock S3 state store, incrementally maintained materialized views, exactly-once barrier checkpointing, 50+ connectors, Iceberg and vector search support.
Risk-sensitive reinforcement learning
Risk-sensitive reinforcement learning is a family of reinforcement learning methods that optimize objectives over the return's distribution, such as variance or conditional value-at-risk, rather than the expected return.
RMSProp
RMSProp is an adaptive gradient-descent optimizer for machine learning, introduced informally by Geoffrey Hinton in 2012 Coursera lectures, that divides each gradient by a decaying average of recent squared gradients.
RNN transducer
The RNN transducer (RNN-T) is a neural network architecture for sequence transduction, introduced by Alex Graves in 2012, and a standard end-to-end model for streaming speech recognition.
Robby the Robot
Robby the Robot is a fictional robot character who first appeared in the 1956 MGM film Forbidden Planet, designed by MGM art director Robert Kinoshita.
Robo-advisor
A robo-advisor is an automated digital investment advisory program that builds and manages a portfolio from an online questionnaire on goals and risk tolerance, with the first launched in 2008.
Roboflow
Roboflow is a Des Moines, Iowa-based computer vision company whose platform handles dataset annotation, model training, and deployment, launched by Joseph Nelson and Brad Dwyer in January 2020.
Robopocalypse
Robopocalypse is a 2011 science fiction novel by Daniel H. Wilson, his debut, in which a sentient AI called Archos turns the world's machines against humanity.
Robot (Lost in Space)
The Robot, also known as Robot B-9, is the robot character of Irwin Allen's television series Lost in Space, which ran on CBS from 1965 to 1968.
Robot series
The Robot series, also called Isaac Asimov's Robot series, is a science fiction sequence of short stories and novels built around the Three Laws of Robotics.
Robust PCA
Robust PCA (RPCA, robust principal component analysis) is a family of PCA methods reliable under gross corruption, splitting a matrix into a low-rank part plus sparse outliers.
RocksDB
RocksDB is an embeddable, persistent key-value store written as a C++ library, developed at Facebook, open-sourced in 2013, and built on Google's LevelDB for fast flash storage.
Role-based access control
Role-based access control (RBAC) is an access control model in which permissions are granted through roles rather than individual users, formally defined by Ferraiolo and Kuhn in 1992.
Rollback (computing)
Rollback is the operation of restoring a system to a prior consistent state by undoing changes, most commonly discarding the updates made by an uncommitted database transaction.