Acronyms is a practical glossary of abbreviations, shortened names, and recurring initialisms used across artificial intelligence, machine learning, statistics, robotics, data systems, and adjacent fields. In strict usage, an acronym is formed from initial letters and pronounced as a word, while an initialism is spoken letter by letter.[1][2] AI writing does not consistently observe that distinction, so this page follows common technical usage and includes both.
The same letters can mean different things across subfields. For example, BN can mean batch normalization or Bayesian network, SSL can mean self-supervised learning or semi-supervised learning, and SVD usually means singular value decomposition but can mean singing voice detection in music information retrieval. Read each entry in the context of its paper, software package, dataset, or application domain. Definitions below are compact identifiers, not substitutes for the linked topic articles or original sources.
See also: Guides, Terms, and Abbreviations.
How to use this glossary
- Capitalization and punctuation can be meaningful. CoT, GloVe, Grad-CAM, i.i.d., and reCAPTCHA preserve source or conventional styling.
- A slash or semicolon marks a genuine context-dependent expansion, not interchangeable wording inside one method.
- Product and project names such as CatBoost, Gurobi, and SWI-Prolog appear because readers encounter them as shortened technical names, even when they are not strict acronyms.
- The glossary favors stable, source-backed expansions. It merges duplicate rows and removes malformed or unsupported expansions from the earlier version.
A
| Term | Meaning |
|---|
| A* | A* Search Algorithm |
| A3C | Asynchronous Advantage Actor-Critic |
| ABAC | Attribute-Based Access Control [4] |
| A/B Testing | A statistical method for comparing two or more treatments or algorithms [3] |
| ACE | Alternating conditional expectation algorithm |
| ACO | Ant Colony Optimization |
| Adam | Optimization algorithm named for adaptive moment estimation; Adam is not a strict initialism [32] |
| ADASYN | Adaptive Synthetic Sampling [75] |
| ADT | Automatic Drum Transcription |
| AE | Autoencoder |
| AGC | Adaptive Gradient Clipping [76] |
| AGI | Artificial general intelligence |
| AI | Artificial intelligence |
| AIaaS | Artificial Intelligence as a Service |
| AL | Active Learning |
| AM | Activation maximization [77] |
| AMR | Abstract Meaning Representation |
| AMT | Automatic music transcription [72] |
| ANI | Artificial Narrow Intelligence |
| ANN | Artificial neural network |
| ANOVA | Analysis of variance |
| API | Application Programming Interface |
| AR | Augmented reality |
| ASI | Artificial superintelligence |
| ASIC | Application-Specific Integrated Circuit |
| ASR | Automatic speech recognition |
| AST | Automated speech translation |
| AUC | Area under the curve, usually the ROC curve unless another curve is named |
| AutoML | Automated Machine Learning [3] |
Scroll sideways for more →
B
| Term | Meaning |
|---|
| BB84 | A quantum key distribution protocol (named after its inventors, Bennett and Brassard, and the year 1984) [59] |
| BBO | Biogeography-Based Optimization |
| BCE | Binary cross-entropy |
| BDT | Boosted Decision Tree |
| BERT | Bidirectional Encoder Representations from Transformers [10] |
| BFS | Breadth-First Search |
| BI | Business Intelligence |
| BiFPN | Bidirectional Feature Pyramid Network [134] |
| BILSTM | Bidirectional Long Short-Term Memory |
| BLEU | Bilingual evaluation understudy [46] |
| BN | Batch normalization; also Bayesian network |
| BNN | Bayesian neural network; also binarized neural network |
| BO | Bayesian Optimization |
| BP | Backpropagation |
| BPE | Byte Pair Encoding [67] |
| BPMF | Bayesian Probabilistic Matrix Factorization [78] |
| BPN | Backpropagation Neural Network |
| BPTT | Backpropagation through time |
| BQML | BigQuery ML [74] |
| BR | Best-Response (in game theory) |
| BRDF | Bidirectional reflectance distribution function |
| BRNN | Bidirectional Recurrent Neural Network |
| BRR | Bayesian ridge regression |
Scroll sideways for more →
C
| Term | Meaning |
|---|
| CAD | Computer-Aided Design |
| CAE | Contractive Autoencoder |
| CAM | Class activation mapping in computer vision; also computer-aided manufacturing |
| CAPTCHA | Completely Automated Public Turing test to tell Computers and Humans Apart [79] |
| CART | Classification and Regression Trees |
| CASE | Computer-Aided Software Engineering |
| CatBoost | Categorical Boosting [80] |
| CAV | Concept activation vector |
| CBAC | Content-Based Access Control |
| CBOW | Continuous Bag of Words |
| CBR | Case-Based Reasoning |
| CCA | Canonical Correlation Analysis |
| CCC | Concordance correlation coefficient; canonical correlation coefficient in some multivariate contexts |
| CCE | Categorical cross-entropy |
| CE | Cross-Entropy |
| CEC | Constant Error Carousel |
| CEGAR | Counterexample-Guided Abstraction Refinement |
| CEGIS | Counterexample-Guided Inductive Synthesis |
| CF | Collaborative filtering |
| cGAN | Conditional Generative Adversarial Network [137] |
| CL | Confident learning; also contrastive learning and continual learning [98][99][51] |
| CLIP | Contrastive Language-Image Pre-Training [14] |
| CLNN | ConditionaL neural network, using the source paper's stylized capitalization [60] |
| CMA | Covariance Matrix Adaptation |
| CMAC | Cerebellar Model Articulation Controller |
| CMA-ES | Covariance Matrix Adaptation Evolution Strategy |
| CNN | Convolutional neural network |
| COIN-OR | Computational Infrastructure for Operations Research |
| ConvNet | Convolutional Neural Network |
| CoT | Chain-of-thought [28] |
| COTE | Collective of Transformation-Based Ensembles [81] |
| CoT prompting | Chain-of-thought prompting [28] |
| CP | Constraint Programming |
| CPLEX | IBM mathematical optimization solver [130] |
| CPN | Colored Petri Nets |
| CRBM | Conditional Restricted Boltzmann Machine |
| CRF | Conditional Random Field |
| CRNN | Convolutional Recurrent Neural Network |
| CSLR | Continuous Sign Language Recognition |
| CSP | Constraint Satisfaction Problem |
| CSV | Comma-separated values |
| CTC | Connectionist Temporal Classification |
| CT-LSTM | Continuous-time long short-term memory; the abbreviation is paper-dependent |
| CTR | Collaborative Topic Regression [82] |
| CUDA | Compute Unified Device Architecture [7] |
| CV | Computer vision; cross-validation; or coefficient of variation, depending on context |
| Cyc | CycL and OpenCyc, a knowledge representation and reasoning system [83] |
Scroll sideways for more →
D
| Term | Meaning |
|---|
| D* | Dynamic A* Search Algorithm |
| DaaS | Data as a Service |
| DAE | Denoising AutoEncoder or Deep AutoEncoder |
| DAML | DARPA Agent Markup Language |
| DART | Dropouts meet Multiple Additive Regression Trees, a tree-boosting regularization method [31] |
| DBM | Deep Boltzmann Machine |
| DBN | Deep belief network |
| DBSCAN | Density-Based Spatial Clustering of Applications with Noise [84] |
| DCAI | Data-centric AI |
| DCGAN | Deep Convolutional Generative Adversarial Network [138] |
| DDPG | Deep Deterministic Policy Gradient |
| DE | Differential evolution |
| DeconvNet | DeConvolutional Neural Network |
| DeepLIFT | Deep Learning Important FeaTures [25] |
| DFS | Depth-First Search |
| DL | Deep learning |
| DM | Data mining; also diffusion model in some machine learning literature |
| DNN | Deep neural network |
| DP | Dynamic Programming |
| DPO | Direct preference optimization [37] |
| DQN | Deep Q-network [34] |
| DR | Detection Rate |
| DRL | Deep Reinforcement Learning |
| DS | Data Science |
| DSR | Deep symbolic regression [85] |
| DSRL | Deep symbolic reinforcement learning [61] |
| DSS | Decision Support System |
| DT | Decision Tree |
| DTD | Deep Taylor Decomposition [86] |
| DWT | Discrete Wavelet Transform |
Scroll sideways for more →
E
| Term | Meaning |
|---|
| EDA | Exploratory data analysis |
| EKF | Extended Kalman Filter |
| ELECTRA | Efficiently Learning an Encoder that Classifies Token Replacements Accurately [13] |
| ELM | Extreme Learning Machine [87] |
| ELMo | Embeddings from Language Models [11] |
| ELU | Exponential Linear Unit [88] |
| EM | Expectation maximization |
| EMD | Earth mover's distance; also empirical mode decomposition and entropy-minimization discretization |
| ERNIE | Enhanced Representation through kNowledge IntEgration [89] |
| ES | Evolution Strategies |
| ESN | Echo State Network |
| ETL | Extract, Transform, Load |
| EXT | Extra-Trees, or extremely randomized trees |
Scroll sideways for more →
F
| Term | Meaning |
|---|
| F1 | F1 score, the harmonic mean of precision and recall |
| FALA | Finite Action-set Learning Automata |
| Fast R-CNN | Fast Region-based Convolutional Network [20] |
| FC | Fully-Connected |
| FCM | Fuzzy C-Means |
| FCN | Fully Convolutional Network |
| FER | Facial Expression Recognition |
| FFT | Fast Fourier transform |
| FL | Federated Learning |
| FLOP | Floating-point operation |
| FLOPS | Floating-point operations per second, more clearly written FLOP/s |
| FM | Foundation model |
| FN | False negative |
| FNN | Feedforward Neural Network |
| FNR | False negative rate |
| FOAF | Friend of a Friend (ontology) |
| FP | False positive |
| FPGA | Field-Programmable Gate Array |
| FPN | Feature Pyramid Network [21] |
| FPR | False positive rate |
| FSL | Few-shot learning |
| FST | Finite state transducer |
| FTL | Federated transfer learning [90] |
| FWA | Fireworks Algorithm |
| FWIoU | Frequency Weighted Intersection over Union |
Scroll sideways for more →
G
| Term | Meaning |
|---|
| GA | Genetic Algorithm |
| GALE | Global Aggregations of Local Explanations [91] |
| GAM | Generalized Additive Model |
| GAN | Generative Adversarial Network [17] |
| GAP | Global Average Pooling |
| GBDT | Gradient Boosted Decision Tree |
| GBM | Gradient Boosting Machine |
| GCN | Graph convolutional network [52] |
| GD | Gradient descent |
| GEBI | Global Explanation for Bias Identification [92] |
| GLCM | Gray Level Co-occurrence Matrix |
| GLM | Generalized Linear Model |
| GLOM | A neural network architecture by Geoffrey Hinton [93] |
| Gloss2Text | A task of transforming raw glosses into meaningful sentences. |
| GloVe | Global Vectors for Word Representation [65] |
| GLPK | GNU Linear Programming Kit |
| GLUE | General Language Understanding Evaluation [50] |
| GMM | Gaussian mixture model |
| GNN | Graph neural network |
| GP | Gaussian process; also genetic programming |
| GPR | Gaussian process regression |
| GPT | Generative Pre-trained Transformer [9] |
| GPU | Graphics processing unit |
| GQA | Grouped-Query Attention [45] |
| Grad-CAM | Gradient-weighted class activation mapping [27] |
| GRU | Gated recurrent unit [94] |
| Gurobi | An optimization solver (named after its founders, Zonghao Gu, Edward Rothberg, and Robert Bixby) |
Scroll sideways for more →
H
| Term | Meaning |
|---|
| HamNoSys | Hamburg Sign Language Notation System [73] |
| HAN | Hierarchical Attention Networks |
| HC | Hierarchical Clustering |
| HDP | Hierarchical Dirichlet process [95] |
| HF | Hugging Face [96] |
| hLDA | Hierarchical Latent Dirichlet allocation |
| HMM | Hidden Markov Model |
| HNN | Hopfield Neural Network |
| HOG | Histogram of Oriented Gradients (feature descriptor) |
| HPC | High Performance Computing |
| HRED | Hierarchical Recurrent Encoder-Decoder |
| HRI | Human-Robot Interaction |
| HSMM | Hidden Semi-Markov Model |
Scroll sideways for more →
I
| Term | Meaning |
|---|
| IaaS | Infrastructure as a Service [5] |
| ICA | Independent component analysis |
| ICP | Iterative Closest Point (point cloud registration) |
| ID3 | Iterative Dichotomiser 3 |
| IDA* | Iterative Deepening A* Search Algorithm |
| IG | Integrated gradients [97] |
| i.i.d. | Independently and identically distributed |
| IID | Independently and identically distributed |
| ILASP | Inductive Learning of Answer Set Programs [100] |
| ILP | Integer linear programming; also inductive logic programming |
| INFD | Explanation Infidelity [101] |
| IoA | Internet of Agents [102] |
| IoE | Internet of Everything |
| IoT | Internet of Things |
| IoU | Jaccard index (intersection over union) |
| IR | Information Retrieval |
| IRCoT | Interleaving Retrieval CoT [131] |
| ISIC | International Skin Imaging Collaboration |
| IVR | Interactive Voice Response |
Scroll sideways for more →
J
| Term | Meaning |
|---|
| JEPA | Joint-embedding predictive architecture [41] |
Scroll sideways for more →
K
| Term | Meaning |
|---|
| KAN | Kolmogorov-Arnold network [40] |
| KB | Knowledge Base |
| KDE | Kernel Density Estimation |
| KF | Kalman Filter |
| kFCV | K-fold cross validation |
| KL | Kullback-Leibler divergence |
| K-Means | K-Means Clustering [3] |
| KNN | K-nearest neighbors |
| KR | Knowledge Representation |
| KRR | Kernel Ridge Regression |
Scroll sideways for more →
L
| Term | Meaning |
|---|
| LAION | Large-scale Artificial Intelligence Open Network [103] |
| LAMA | LAnguage Model Analysis |
| LaMDA | Language Models for Dialog Applications [15] |
| LBP | Local Binary Pattern (texture descriptor) |
| LDA | Latent Dirichlet allocation; also linear discriminant analysis [66][135] |
| LEPOR | Length Penalty, Precision, n-gram Position difference Penalty and Recall [49] |
| LightGBM | Light Gradient Boosting Machine [104] |
| LIME | Local Interpretable Model-agnostic Explanations [105] |
| LINGO | A software for linear, nonlinear, and integer optimization |
| LL | Lifelong learning |
| LLM | Large language model [3] |
| LLS | Linear least squares |
| LMNN | Large Margin Nearest Neighbor [106] |
| LoRA | Low-rank adaptation [35] |
| LP | Linear Programming |
| LRP | Layer-wise Relevance Propagation |
| LSA | Latent semantic analysis |
| LSI | Latent Semantic Indexing |
| LSTM | Long short-term memory |
| LSTM-CRF | Long Short-Term Memory with Conditional Random Field |
| LTR | Learning To Rank |
| LVQ | Learning Vector Quantization |
Scroll sideways for more →
M
| Term | Meaning |
|---|
| M2M | Machine to Machine |
| MADE | Masked Autoencoder for Distribution Estimation [107] |
| MAE | Mean absolute error |
| MAF | Masked Autoregressive Flows [108] |
| MAIRL | Multi-Agent Inverse Reinforcement Learning |
| MAP | Maximum A Posteriori (MAP) Estimation |
| MAPE | Mean absolute percentage error |
| MARL | Multi-Agent Reinforcement Learning |
| MART | Multiple Additive Regression Trees [31] |
| MaxEnt | Maximum Entropy |
| MAXSAT | Maximum Satisfiability Problem |
| MCLNN | Masked ConditionaL Neural Networks [60] |
| MCMC | Markov Chain Monte Carlo |
| MCP | Model Context Protocol [54] |
| MCTS | Monte Carlo Tree Search |
| MDL | Minimum description length (MDL) principle |
| MDN | Mixture Density Network |
| MDP | Markov Decision Process |
| MDRNN | Multidimensional recurrent neural network |
| MER | Music Emotion Recognition |
| METEOR | Metric for Evaluation of Translation with Explicit ORdering [48] |
| MHA | Multi-head attention [68] |
| MIL | Multiple Instance Learning |
| MILP | Mixed-Integer Linear Programming |
| MIoU | Mean Intersection over Union |
| MIP | Mixed-Integer Programming |
| ML | Machine learning |
| MLA | Multi-head latent attention [44] |
| MLaaS | Machine Learning as a Service |
| MLE | Maximum Likelihood Estimation |
| MLLM | Multimodal large language model |
| MLM | Masked language modeling or masked language model |
| MLP | Multi-Layer Perceptron |
| MMI | Maximum Mutual Information |
| MNIST | Modified National Institute of Standards and Technology database [3] |
| MoA | Mixture of Agents [109] |
| MoE | Mixture of Experts [3] |
| MOEA | Multi-Objective Evolutionary Algorithm |
| MPA | Mean Pixel Accuracy |
| MQA | Multi-Query Attention [45] |
| MR | Mixed Reality |
| MRF | Markov Random Field |
| MRR | Mean Reciprocal Rank |
| MRS | Music Recommender System |
| MSE | Mean squared error |
| MSR | Music Style Recognition |
| MTL | Multi-Task Learning |
Scroll sideways for more →
N
| Term | Meaning |
|---|
| NARX | Nonlinear AutoRegressive with eXogenous input (neural network model) |
| NAS | Neural Architecture Search [3] |
| NB | Naive Bayes |
| NDCG | Normalized Discounted Cumulative Gain |
| NE | Nash Equilibrium (in game theory) |
| NEAT | NeuroEvolution of Augmenting Topologies [110] |
| NER | Named entity recognition |
| NEST | Neural Simulation Tool [111] |
| NF | Normalizing Flow |
| NFL | No Free Lunch (NFL) theorem |
| NISQ | Noisy intermediate-scale quantum |
| NLG | Natural Language Generation |
| NLP | Natural Language Processing |
| NLU | Natural Language Understanding |
| NMF | Non-negative matrix factorization |
| NMS | Non Maximum Suppression |
| NMT | Neural Machine Translation |
| NN | Neural network |
| NRMSE | Normalized RMSE |
| NSGA-II | Non-dominated Sorting Genetic Algorithm II [112] |
| NST | Neural style transfer |
| NTM | Neural Turing Machine [113] |
| NuSVC | Nu-Support Vector Classification |
| NuSVR | Nu-Support Vector Regression |
Scroll sideways for more →
O
| Term | Meaning |
|---|
| OCR | Optical character recognition |
| OD | Object Detection |
| ODF | Onset Detection Function |
| OIL | Ontology Inference Layer |
| OLR | Ordinary Linear Regression |
| OLS | Ordinary Least Squares |
| OMNeT++ | Objective Modular Network Testbed in C++ |
| OMR | Optical music recognition |
| OOF | Out-of-fold |
| ORB | Oriented FAST and Rotated BRIEF (feature descriptor) |
| OWL | Web Ontology Language [6] |
Scroll sideways for more →
P
| Term | Meaning |
|---|
| PA | Pixel Accuracy |
| PaaS | Platform as a Service [5] |
| PaLM | Pathways Language Model [16] |
| PBAC | Policy-Based Access Control |
| PCA | Principal component analysis |
| PCL | Point Cloud Library (3D perception) |
| PEFT | Parameter-efficient fine-tuning [70] |
| PEGASUS | Pre-training with Extracted Gap-sentences for Abstractive Summarization [114] |
| PF | Particle Filter |
| PLSI | Probabilistic Latent Semantic Indexing |
| PM | Project Manager |
| PMF | Probabilistic Matrix Factorization |
| PMI | Pointwise Mutual Information |
| PNN | Probabilistic Neural Network |
| POC | Proof of Concept |
| POMDP | Partially Observable Markov Decision Process |
| POS | Part of Speech (POS) Tagging |
| PPL | Perplexity (a measure of language model performance) |
| PPMI | Positive Pointwise Mutual Information |
| PPO | Proximal Policy Optimization [33] |
| PReLU | Parametric rectified linear unit [115] |
| PRM | Probabilistic Roadmap (motion planning algorithm) |
| PSO | Particle Swarm Optimization |
| PU | Positive-unlabeled learning [116] |
| PYTM | Pitman-Yor topic model |
Scroll sideways for more →
Q
| Term | Meaning |
|---|
| QA | Question Answering |
| QAOA | Quantum Approximate Optimization Algorithm |
| QAP | Quadratic Assignment Problem |
| QEC | Quantum Error Correction |
| QFT | Quantum Fourier Transform |
| QIP | Quantum Information Processing |
| QKD | Quantum Key Distribution |
| QLoRA | Quantized low-rank adaptation [36] |
| QML | Quantum Machine Learning |
| QNN | Quantum Neural Network |
| QP | Quadratic Programming |
| QPE | Quantum Phase Estimation |
Scroll sideways for more →
R
| Term | Meaning |
|---|
| R2 | R-squared |
| RAG | Retrieval-Augmented Generation [30] |
| RandNN | Random Neural Network |
| RANSAC | RANdom SAmple Consensus |
| RBAC | Role-based access control |
| RBF | Radial Basis Function |
| RBFNN | Radial Basis Function Neural Network |
| RBM | Restricted Boltzmann Machine |
| R-CNN | Region-based Convolutional Neural Network [20] |
| RDF | Resource Description Framework [6] |
| ReAct | Reasoning and acting [29] |
| REALM | Retrieval-Augmented Language Model Pre-Training [132] |
| reCAPTCHA | Google's reCAPTCHA challenge service; "reverse CAPTCHA" is not its expansion [58] |
| ReLU | Rectified Linear Unit [3] |
| REPTree | Reduced Error Pruning Tree |
| RETRO | Retrieval-Enhanced Transformer [133] |
| RF | Random forest |
| RFE | Recursive Feature Elimination |
| RGB | Red Green Blue color model |
| RICNN | Rotation Invariant Convolutional Neural Network |
| RIM | Recurrent inference machine [62] |
| RIPPER | Repeated Incremental Pruning to Produce Error Reduction |
| RISE | Random Interval Spectral Ensemble; also Randomized Input Sampling for Explanation [117] |
| RL | Reinforcement learning |
| RLAIF | Reinforcement learning from AI feedback [38] |
| RLHF | Reinforcement Learning from Human Feedback [69] |
| RMSE | Root mean squared error |
| RMSLE | Root mean squared logarithmic error |
| RMSprop | Root Mean Square Propagation |
| RNN | Recurrent neural network |
| RNNLM | Recurrent Neural Network Language Model (RNNLM) |
| RoBERTa | Robustly Optimized BERT Pretraining Approach [118] |
| ROC | Receiver operating characteristic |
| ROI | Region Of Interest |
| RoPE | Rotary position embedding [39] |
| ROS | Robot Operating System [119] |
| ROUGE | Recall-Oriented Understudy for Gisting Evaluation (NLP metric) [47] |
| RPA | Robotic Process Automation |
| RR | Ridge Regression |
| RRT | Rapidly-exploring Random Tree (motion planning algorithm) |
| RSI | Recursive self-improvement [120] |
| RTRL | Real-Time Recurrent Learning |
Scroll sideways for more →
S
| Term | Meaning |
|---|
| SA | Simulated annealing |
| SaaS | Software as a Service [5] |
| SAC | Soft Actor-Critic |
| SAE | Sparse autoencoder; also stacked autoencoder |
| SAM | Segment Anything Model, introduced in Segment Anything [24] |
| SARSA | State-Action-Reward-State-Action |
| SAT | Boolean satisfiability problem |
| SBAC | Situation-Based Access Control |
| SBM | Stochastic block model |
| SBO | Structured Bayesian optimization |
| SBSE | Search-based software engineering |
| SCIP | Solving Constraint Integer Programs |
| SDAE | Stacked denoising autoencoder [140] |
| seq2seq | Sequence to Sequence Learning |
| SER | Sentence Error Rate |
| SFT | Supervised fine-tuning [71] |
| SGBoost | Stochastic Gradient Boosting |
| SGD | Stochastic gradient descent [3] |
| SGVB | Stochastic Gradient Variational Bayes |
| SHAP | SHapley Additive exPlanations [26] |
| SIFT | Scale-Invariant Feature Transform (feature detection) |
| SL | Supervised learning |
| SLAM | Simultaneous Localization and Mapping |
| SLDS | Switching Linear Dynamical System |
| SLM | Small Language Model |
| SLP | Single-Layer Perceptron |
| SLT | Sign Language Translation [73] |
| SMA* | Simplified Memory-bounded A* Search Algorithm |
| SMBO | Sequential Model-Based Optimization |
| SMO | Sequential Minimal Optimization |
| SMOTE | Synthetic Minority Over-sampling Technique [121] |
| SNN | Spiking neural network; also sparse neural network |
| SOM | Self-Organizing Map |
| SOTA | State of the Art |
| SPARQL | SPARQL Protocol and RDF Query Language [6] |
| SPM | SentencePiece Model (subword tokenization) [63] |
| SpRAy | Spectral Relevance Analysis [122] |
| SSD | Single Shot MultiBox Detector |
| SSL | Self-supervised learning; also semi-supervised learning |
| SSM | State space model [42] |
| ST | Style transfer |
| STaR | Self-Taught Reasoner [123] |
| STDP | Spike Timing-Dependent Plasticity |
| STL | Self-taught learning [124] |
| SUMO | Simulation of Urban MObility [55] |
| SURF | Speeded-Up Robust Features (feature detection) |
| SVC | Support Vector Classification |
| SVD | Singular value decomposition; also singing voice detection |
| SVM | Support vector machine |
| SVR | Support Vector Regression |
| SVS | Singing Voice Separation |
| SWI-Prolog | An implementation of the Prolog programming language [57] |
Scroll sideways for more →
T
| Term | Meaning |
|---|
| T5 | Text-To-Text Transfer Transformer [12] |
| TD | Temporal Difference |
| TDA | Topological data analysis [125] |
| TDE | Temporal Dictionary Ensemble [139] |
| tf-idf | term frequency-inverse document frequency |
| THAID | THeta Automatic Interaction Detection |
| TL | Transfer Learning |
| TN | True negative |
| TNR | True negative rate |
| ToM | Theory of Mind |
| ToT | Tree of thoughts [53] |
| TP | True positive |
| TPOT | Tree-based Pipeline Optimization Tool |
| TPR | True positive rate |
| TPU | Tensor Processing Unit [8] |
| TRPO | Trust Region Policy Optimization |
| TS | Time series; also tabu search |
| TSF | Time Series Forest [81] |
| t-SNE | t-distributed stochastic neighbor embedding [126] |
| TSP | Traveling Salesman Problem |
| TTS | Text-to-Speech |
Scroll sideways for more →
U
| Term | Meaning |
|---|
| UCT | Upper Confidence bounds applied to Trees (Monte Carlo Tree Search variant) |
| UDA | Unsupervised Data Augmentation [127] |
| UKF | Unscented Kalman Filter |
| UL | Unsupervised learning |
| ULMFiT | Universal Language Model Fine-Tuning |
| UMAP | Uniform Manifold Approximation and Projection [64] |
| USM | Universal Speech Model |
Scroll sideways for more →
V
| Term | Meaning |
|---|
| VAD | Voice Activity Detection |
| VAE | Variational AutoEncoder [18] |
| VGG | Visual Geometry Group |
| VHRED | Variational Hierarchical Recurrent Encoder-Decoder [128] |
| VISSIM | Verkehr In Stadten - SIMulationsmodell, a traffic microsimulation system [56] |
| ViT | Vision Transformer [23] |
| VLA | Vision-language-action model [43] |
| VLM | Vision-Language Model |
| V-Net | A fully convolutional network for volumetric medical image segmentation [141] |
| VQE | Variational Quantum Eigensolver |
| VQ-VAE | Vector-quantized variational autoencoder [136] |
| VR | Virtual reality |
| VRP | Vehicle Routing Problem |
| VUI | Voice User Interface |
Scroll sideways for more →
W
| Term | Meaning |
|---|
| WCSP | Weighted Constraint Satisfaction Problem |
| WER | Word Error Rate |
| WFST | Weighted finite-state transducer (WFST) |
| WGAN | Wasserstein Generative Adversarial Network [19] |
| WMA | Weighted Majority Algorithm |
| WPE | Weighted Prediction Error |
Scroll sideways for more →
X
| Term | Meaning |
|---|
| XAI | Explainable Artificial Intelligence |
| XGBoost | eXtreme Gradient Boosting [129] |
| XOR | Exclusive OR (a common problem in neural networks) |
Scroll sideways for more →
Y
| Term | Meaning |
|---|
| YOLO | You Only Look Once [22] |
Scroll sideways for more →
Z
| Term | Meaning |
|---|
| ZSL | Zero-Shot Learning |
Scroll sideways for more →
References
- ^Cambridge Dictionary. "acronym." dictionary.cambridge.org/...acronym
- ^Cambridge Dictionary. "initialism." dictionary.cambridge.org/...initialism
- ^Google for Developers. "Machine Learning Glossary." developers.google.com/...glossary
- ^NIST. "Attribute Based Access Control." csrc.nist.gov/...attribute_based_access_control
- ^Mell, P., and Grance, T. (2011). "The NIST Definition of Cloud Computing." csrc.nist.gov/...final
- ^World Wide Web Consortium. "Semantic Web Standards." w3.org/...semanticweb
- ^NVIDIA. "CUDA Documentation." docs.nvidia.com/cuda
- ^Google Cloud. "Cloud TPU documentation." cloud.google.com/...docs
- ^Eloundou, T., Manning, S., Mishkin, P., and Rock, D. (2023). "GPTs are GPTs: An early look at the labor market impact potential of large language models." openai.com/...gpts-are-gpts
- ^Devlin, J., et al. (2019). "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding." aclanthology.org/N19-1423
- ^Peters, M. E., et al. (2018). "Deep contextualized word representations." aclanthology.org/N18-1202
- ^Raffel, C., et al. (2020). "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer." jmlr.org/...20-074
- ^Clark, K., et al. (2020). "ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators." arxiv.org/...2003.10555
- ^Radford, A., et al. (2021). "Learning Transferable Visual Models From Natural Language Supervision." openai.com/...clip
- ^Thoppilan, R., et al. (2022). "LaMDA: Language Models for Dialog Applications." arxiv.org/...2201.08239
- ^Chowdhery, A., et al. (2022). "PaLM: Scaling Language Modeling with Pathways." arxiv.org/...2204.02311
- ^Goodfellow, I., et al. (2014). "Generative Adversarial Nets." papers.nips.cc/...5423-generative-adversarial-nets
- ^Kingma, D. P., and Welling, M. (2013). "Auto-Encoding Variational Bayes." arxiv.org/...1312.6114
- ^Arjovsky, M., Chintala, S., and Bottou, L. (2017). "Wasserstein Generative Adversarial Networks." proceedings.mlr.press/...arjovsky17a
- ^Girshick, R. (2015). "Fast R-CNN." openaccess.thecvf.com/...ast_R-CNN_ICCV_2015_paper
- ^Lin, T.-Y., et al. (2017). "Feature Pyramid Networks for Object Detection." openaccess.thecvf.com/..._Networks_CVPR_2017_paper
- ^Redmon, J., et al. (2016). "You Only Look Once: Unified, Real-Time Object Detection." openaccess.thecvf.com/...Only_Look_CVPR_2016_paper
- ^Dosovitskiy, A., et al. (2020). "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale." arxiv.org/...2010.11929
- ^Kirillov, A., et al. (2023). "Segment Anything." arxiv.org/...2304.02643
- ^Shrikumar, A., Greenside, P., and Kundaje, A. (2017). "Learning Important Features Through Propagating Activation Differences." proceedings.mlr.press/...shrikumar17a
- ^Lundberg, S. M., and Lee, S.-I. (2017). "A Unified Approach to Interpreting Model Predictions." papers.nips.cc/...o-interpreting-model-predictions
- ^Selvaraju, R. R., et al. (2017). "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization." openaccess.thecvf.com/...lanations_ICCV_2017_paper
- ^Wei, J., et al. (2022). "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models." arxiv.org/...2201.11903
- ^Yao, S., et al. (2022). "ReAct: Synergizing Reasoning and Acting in Language Models." arxiv.org/...2210.03629
- ^Lewis, P., et al. (2020). "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks." papers.neurips.cc/...780e1bc26945df7481e5-Abstract
- ^Rashmi, K. V., and Gilad-Bachrach, R. (2015). "DART: Dropouts meet Multiple Additive Regression Trees." proceedings.mlr.press/...korlakaivinayak15
- ^Kingma, D. P., and Ba, J. (2014). "Adam: A Method for Stochastic Optimization." arxiv.org/...1412.6980
- ^Schulman, J., et al. (2017). "Proximal Policy Optimization Algorithms." arxiv.org/...1707.06347
- ^Mnih, V., et al. (2015). "Human-level control through deep reinforcement learning." nature.com/...nature14236
- ^Hu, E. J., et al. (2021). "LoRA: Low-Rank Adaptation of Large Language Models." arxiv.org/...2106.09685
- ^Dettmers, T., et al. (2023). "QLoRA: Efficient Finetuning of Quantized LLMs." arxiv.org/...2305.14314
- ^Rafailov, R., et al. (2023). "Direct Preference Optimization: Your Language Model is Secretly a Reward Model." arxiv.org/...2305.18290
- ^Lee, H., et al. (2023). "RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback." arxiv.org/...2309.00267
- ^Su, J., et al. (2021). "RoFormer: Enhanced Transformer with Rotary Position Embedding." arxiv.org/...2104.09864
- ^Liu, Z., et al. (2024). "KAN: Kolmogorov-Arnold Networks." arxiv.org/...2404.19756
- ^Assran, M., et al. (2023). "Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture." openaccess.thecvf.com/...hitecture_CVPR_2023_paper
- ^Gu, A., and Dao, T. (2023). "Mamba: Linear-Time Sequence Modeling with Selective State Spaces." arxiv.org/...2312.00752
- ^Kim, M. J., et al. (2024). "OpenVLA: An Open-Source Vision-Language-Action Model." arxiv.org/...2406.09246
- ^DeepSeek-AI (2024). "DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model." arxiv.org/...2405.04434
- ^Ainslie, J., et al. (2023). "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints." aclanthology.org/2023.emnlp-main.298
- ^Papineni, K., et al. (2002). "BLEU: a Method for Automatic Evaluation of Machine Translation." aclanthology.org/P02-1040
- ^Lin, C.-Y. (2004). "ROUGE: A Package for Automatic Evaluation of Summaries." aclanthology.org/W04-1013
- ^Banerjee, S., and Lavie, A. (2005). "METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments." aclanthology.org/W05-0909
- ^Han, A. L. F., Wong, D. F., and Chao, L. S. (2012). "LEPOR: A Robust Evaluation Metric for Machine Translation with Augmented Factors." aclanthology.org/C12-2044
- ^Wang, A., et al. (2018). "GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding." openreview.net/forum
- ^Lopez-Paz, D., and Ranzato, M. (2017). "Gradient Episodic Memory for Continual Learning." papers.nips.cc/...ic-memory-for-continual-learning
- ^Kipf, T. N., and Welling, M. (2016). "Semi-Supervised Classification with Graph Convolutional Networks." arxiv.org/...1609.02907
- ^Yao, S., et al. (2023). "Tree of Thoughts: Deliberate Problem Solving with Large Language Models." arxiv.org/...2305.10601
- ^Model Context Protocol. "Specification." modelcontextprotocol.io/specification
- ^Eclipse Foundation. "SUMO: Simulation of Urban MObility." eclipse.dev/sumo
- ^Schubert, R., et al. (2024). "An open-source VISSIM calibration framework." pmc.ncbi.nlm.nih.gov/...PMC10878954
- ^Wielemaker, J., et al. (2010). "SWI-Prolog." arxiv.org/...1011.5332
- ^Google. "What is reCAPTCHA?" support.google.com/...6080904
- ^Bennett, C. H., and Brassard, G. (1984). "Quantum cryptography: Public key distribution and coin tossing." doi.org/...j.tcs.2014.05.025
- ^Alqahtani, A., et al. (2018). "ConditionaL Neural Networks." arxiv.org/...1804.02665
- ^Garnelo, M., et al. (2016). "Towards Deep Symbolic Reinforcement Learning." arxiv.org/...1609.05518
- ^Putzky, P., and Welling, M. (2017). "Recurrent Inference Machines for Solving Inverse Problems." arxiv.org/...1706.04008
- ^Kudo, T., and Richardson, J. (2018). "SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing." aclanthology.org/D18-2012
- ^McInnes, L., Healy, J., and Melville, J. (2018). "UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction." arxiv.org/...1802.03426
- ^Pennington, J., Socher, R., and Manning, C. D. (2014). "GloVe: Global Vectors for Word Representation." aclanthology.org/D14-1162
- ^Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). "Latent Dirichlet Allocation." jmlr.org/...blei03a
- ^Sennrich, R., Haddow, B., and Birch, A. (2016). "Neural Machine Translation of Rare Words with Subword Units." aclanthology.org/P16-1162
- ^Vaswani, A., et al. (2017). "Attention Is All You Need." arxiv.org/...1706.03762
- ^Ouyang, L., et al. (2022). "Training language models to follow instructions with human feedback." arxiv.org/...2203.02155
- ^Hugging Face. "Parameter-efficient fine-tuning." huggingface.co/...peft
- ^Hugging Face. "Supervised Fine-tuning Trainer." huggingface.co/...sft_trainer
- ^Wiggins, G. A., et al. (2024). "Automatic Music Transcription: A Survey." arxiv.org/...2406.15249
- ^Koller, O. (2023). "Quantitative survey of the state of the art in sign language recognition." link.springer.com/...s10209-023-00992-1
- ^Google Cloud. "What is BigQuery ML?" cloud.google.com/...bqml-introduction
- ^He, H., et al. (2008). "ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning." doi.org/...IJCNN.2008.4633969
- ^Brock, A., De, S., Smith, S. L., and Simonyan, K. (2021). "High-Performance Large-Scale Image Recognition Without Normalization." arxiv.org/...2102.06171
- ^Erhan, D., et al. (2010). "Why Does Unsupervised Pre-training Help Deep Learning?" proceedings.mlr.press/...erhan10a
- ^Salakhutdinov, R., and Mnih, A. (2008). "Bayesian Probabilistic Matrix Factorization Using Markov Chain Monte Carlo." cs.toronto.edu/...bpmf.pdf
- ^von Ahn, L., et al. (2003). "CAPTCHA: Using Hard AI Problems for Security." doi.org/...966389.966390
- ^Prokhorenkova, L., et al. (2018). "CatBoost: unbiased boosting with categorical features." proceedings.neurips.cc/...c41c24863285549-Abstract
- ^Bagnall, A., et al. (2017). "The great time series classification bake off." arxiv.org/...1602.01711
- ^Wang, C., and Blei, D. M. (2011). "Collaborative Topic Modeling for Recommending Scientific Articles." dl.acm.org/...2020408.2020480
- ^Cycorp. "The Cyc Knowledge Base." cyc.com/...cyc-knowledge-base
- ^Ester, M., et al. (1996). "A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise." dl.acm.org/...3001460.3001507
- ^Petersen, B. K., et al. (2019). "Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients." arxiv.org/...1912.04871
- ^Montavon, G., et al. (2017). "Explaining nonlinear classification decisions with deep Taylor decomposition." doi.org/...j.patcog.2016.11.008
- ^Huang, G.-B., Zhu, Q.-Y., and Siew, C.-K. (2006). "Extreme learning machine: Theory and applications." doi.org/...j.neucom.2005.12.126
- ^Clevert, D.-A., Unterthiner, T., and Hochreiter, S. (2015). "Fast and Accurate Deep Network Learning by Exponential Linear Units." arxiv.org/...1511.07289
- ^Sun, Y., et al. (2019). "ERNIE: Enhanced Representation through Knowledge Integration." arxiv.org/...1904.09223
- ^Liu, Y., et al. (2018). "Secure Federated Transfer Learning." arxiv.org/...1812.03337
- ^van der Linden, I., Haned, H., and Kanoulas, E. (2019). "Global Aggregations of Local Explanations for Black Box models." arxiv.org/...1907.03039
- ^Mikolajczyk-Barela, A. (2023). "Data augmentation and explainability for bias discovery and mitigation in deep learning." arxiv.org/...2308.09464
- ^Hinton, G. (2021). "How to represent part-whole hierarchies in a neural network." arxiv.org/...2102.12627
- ^Cho, K., et al. (2014). "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation." arxiv.org/...1406.1078
- ^Teh, Y. W., et al. (2004). "Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes." proceedings.neurips.cc/...9739320d7a51c02-Abstract
- ^Hugging Face. "Documentation." huggingface.co/docs
- ^Sundararajan, M., Taly, A., and Yan, Q. (2017). "Axiomatic Attribution for Deep Networks." proceedings.mlr.press/...sundararajan17a
- ^Northcutt, C. G., Jiang, L., and Chuang, I. L. (2021). "Confident Learning: Estimating Uncertainty in Dataset Labels." jair.org/...12125
- ^Chen, T., et al. (2020). "A Simple Framework for Contrastive Learning of Visual Representations." proceedings.mlr.press/...chen20j
- ^Law, M., Russo, A., and Broda, K. (2021). "ILASP in the Fast Lane." ijcai.org/...0223.pdf
- ^Yeh, C.-K., et al. (2019). "On the (In)fidelity and Sensitivity for Explanations." arxiv.org/...1901.09392
- ^Chen, W., et al. (2024). "Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence." arxiv.org/...2407.07061
- ^Schuhmann, C., et al. (2022). "LAION-5B: An open large-scale dataset for training next generation image-text models." arxiv.org/...2210.08402
- ^Ke, G., et al. (2017). "LightGBM: A Highly Efficient Gradient Boosting Decision Tree." proceedings.neurips.cc/...669bdd9eb6b76fa-Abstract
- ^Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). "Why Should I Trust You? Explaining the Predictions of Any Classifier." arxiv.org/...1602.04938
- ^Weinberger, K. Q., and Saul, L. K. (2009). "Distance Metric Learning for Large Margin Nearest Neighbor Classification." jmlr.org/...weinberger09a
- ^Germain, M., et al. (2015). "MADE: Masked Autoencoder for Distribution Estimation." proceedings.mlr.press/...germain15
- ^Papamakarios, G., Pavlakou, T., and Murray, I. (2017). "Masked Autoregressive Flow for Density Estimation." papers.nips.cc/...sive-flow-for-density-estimation
- ^Wang, J., et al. (2024). "Mixture-of-Agents Enhances Large Language Model Capabilities." arxiv.org/...2406.04692
- ^Stanley, K. O., and Miikkulainen, R. (2002). "Evolving Neural Networks through Augmenting Topologies." nn.cs.utexas.edu/...stanley.ec02.pdf
- ^NEST Initiative. "NEST Simulator documentation." nest-simulator.org
- ^Deb, K., et al. (2002). "A fast and elitist multiobjective genetic algorithm: NSGA-II." doi.org/...4235.996017
- ^Graves, A., Wayne, G., and Danihelka, I. (2014). "Neural Turing Machines." arxiv.org/...1410.5401
- ^Zhang, J., et al. (2020). "PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization." proceedings.mlr.press/...zhang20ae
- ^He, K., et al. (2015). "Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification." openaccess.thecvf.com/...Deep_into_ICCV_2015_paper
- ^Elkan, C., and Noto, K. (2008). "Learning classifiers from only positive and unlabeled data." cseweb.ucsd.edu/...posonly.pdf
- ^Petsiuk, V., Das, A., and Saenko, K. (2018). "RISE: Randomized Input Sampling for Explanation of Black-box Models." arxiv.org/...1806.07421
- ^Liu, Y., et al. (2019). "RoBERTa: A Robustly Optimized BERT Pretraining Approach." arxiv.org/...1907.11692
- ^Open Robotics. "ROS Documentation." docs.ros.org
- ^Yudkowsky, E. (2007). "Artificial Intelligence as a Positive and Negative Factor in Global Risk." intelligence.org/...AIPosNegFactor.pdf
- ^Chawla, N. V., et al. (2002). "SMOTE: Synthetic Minority Over-sampling Technique." jair.org/...10302
- ^Lapuschkin, S., et al. (2019). "Unmasking Clever Hans Predictors and Assessing What Machines Really Learn." arxiv.org/...1902.10178
- ^Zelikman, E., et al. (2022). "STaR: Bootstrapping Reasoning With Reasoning." arxiv.org/...2203.14465
- ^Raina, R., et al. (2007). "Self-taught learning: transfer learning from unlabeled data." dl.acm.org/...1273496.1273592
- ^Hensel, F., et al. (2021). "A Survey of Topological Machine Learning Methods." arxiv.org/...2101.05778
- ^van der Maaten, L., and Hinton, G. (2008). "Visualizing Data using t-SNE." jmlr.org/...vandermaaten08a
- ^Xie, Q., et al. (2019). "Unsupervised Data Augmentation for Consistency Training." arxiv.org/...1904.12848
- ^Serban, I. V., et al. (2016). "A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues." arxiv.org/...1605.06069
- ^Chen, T., and Guestrin, C. (2016). "XGBoost: A Scalable Tree Boosting System." doi.org/...2939672.2939785
- ^IBM. "CPLEX Optimizer documentation." ibm.com/...icos
- ^Trivedi, H., et al. (2022). "Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions." arxiv.org/...2212.10509
- ^Guu, K., et al. (2020). "REALM: Retrieval-Augmented Language Model Pre-Training." arxiv.org/...2002.08909
- ^Borgeaud, S., et al. (2021). "Improving language models by retrieving from trillions of tokens." arxiv.org/...2112.04426
- ^Tan, M., Pang, R., and Le, Q. V. (2020). "EfficientDet: Scalable and Efficient Object Detection." openaccess.thecvf.com/...Detection_CVPR_2020_paper
- ^Scikit-learn developers. "Linear and Quadratic Discriminant Analysis." scikit-learn.org/...lda_qda
- ^van den Oord, A., Vinyals, O., and Kavukcuoglu, K. (2017). "Neural Discrete Representation Learning." arxiv.org/...1711.00937
- ^Mirza, M., and Osindero, S. (2014). "Conditional Generative Adversarial Nets." arxiv.org/...1411.1784
- ^Radford, A., Metz, L., and Chintala, S. (2015). "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks." arxiv.org/...1511.06434
- ^Middlehurst, M., Large, J., and Bagnall, A. (2021). "The Temporal Dictionary Ensemble (TDE) Classifier for Time Series Classification." arxiv.org/...2105.03841
- ^Vincent, P., et al. (2010). "Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion." jmlr.csail.mit.edu/...vincent10a
- ^Milletari, F., Navab, N., and Ahmadi, S.-A. (2016). "V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation." arxiv.org/...1606.04797
