DataTerminology.comManages the deployment, monitoring, and lifecycle of machine learning models in production
Terms (1573)
- ๐ ฐ๏ธ A-B Test
- ๐ฎ A2C
- ๐ค A3C
- ๐ง AGIEval
- โ๏ธ AI Accelerator
- ๐ค AI Alignment
- โ๏ธ AI Governance
- ๐งญ AI Management Systems
- ๐งญ AI Risk Management
- ๐ก๏ธ AI Safety
- โ AIME
- ๐ค ALBERT
- ๐ผ๏ธ ALIGN
- ๐ฅ๏ธ AMD MI300X
- ๐งฉ ARC Challenge
- ๐ AUC
- ๐ AUC Score
- ๐ช AWQ
- ๐งฎ AWQ Quantization
- ๐ชจ AWS Bedrock
- ๐ง AWS SageMaker
- ๐งฉ AWS Step Functions
- ๐งช Ablation Study
- ๐ Accelerate Library
- ๐ Access Control
- ๐ Accumulated Local Effects
- โ Accuracy
- ๐ค Acoustic Model
- ๐ฎ Action
- ๐ง Action Model Learning
- ๐ฎ Action Space
- โก Activation Function
- ๐ง Active Learning
- โ๏ธ Active Metadata
- ๐ญ Actor-Critic
- ๐ AdaBoost
- โ๏ธ Adagrad
- โ๏ธ Adam
- โ๏ธ Adam Optimization
- โ๏ธ Adam Optimizer
- โ๏ธ AdamW
- ๐ Adapters
- ๐ Adaptive Algorithm
- โ๏ธ Adaptive Optimizers
- ๐ฏ Advantage Function
- โ ๏ธ Adversarial Examples
- ๐ก๏ธ Adversarial Robustness
- ๐ก๏ธ Adversarial Training
- ๐ค Agent
- ๐๏ธ Agent Architecture
- ๐งช AgentBench
- ๐ค Agentic AI
- ๐ค Agentic Workflows
- ๐ Akaike Information Criterion
- ๐จ Alerting
- ๐ AlexNet
- โ ๏ธ Algorithmic Bias
- โ๏ธ Alignment
- ๐งญ Alignment Funnel
- ๐ฆ AlpacaEval
- ๐งฌ AlphaFold 3
- ๐ Amazon EMR
- ๐จ Amazon SQS
- ๐ง Amazon SageMaker
- ๐งญ Annoy
- ๐จ Anomaly Detection
- ๐๏ธ Anonymization
- ๐ง Anthropic API
- ๐ Apache Airflow
- ๐น Apache Arrow
- ๐ง Apache Beam
- ๐ Apache Flink
- ๐๏ธ Apache Hudi
- ๐ง Apache Iceberg
- ๐งต Apache Kafka
- โ๏ธ Apache Spark
- โก Apache Spark SQL
- โก Apache Spark Structured Streaming
- โ Append-Only
- ๐ ๏ธ Applied AI
- ๐ Approval Gates
- ๐งญ Approximate Nearest Neighbor
- ๐ฏ Approximate Nearest Neighbor Search
- ๐ Area Under the Curve
- ๐๏ธ Arena Elo
- ๐ Arrow Flight
- ๐ฆ Artifact Management
- ๐ฆ Artifact Registry
- ๐๏ธ Artifact Repository
- ๐งฑ Artifacts
- ๐ค Artificial Intelligence
- ๐ง Artificial Super Intelligence
- ๐ฏ Asynchronous Successive Halving Algorithm
- ๐ฏ At-Most-Once Delivery
- ๐ง Attention Head
- ๐ฏ Attention Mechanism
- ๐งฒ Attention Sink
- ๐ Attention with Linear Biases
- ๐ง Audio Embeddings
- ๐ต Audio Generation
- ๐ง Audio Steganalysis
- ๐งพ Auditability
- ๐ง AutoAWQ
- โ๏ธ AutoGPTQ
- โ๏ธ AutoML
- ๐ Autocorrelation Function
- ๐งฉ Autoencoder
- ๐งฎ Autograd
- ๐ค Automated Governance
- ๐ค Automated Testing
- โ Automatic Differentiation
- โ๏ธ Automatic Mixed Precision
- ๐ค Automation
- ๐ฆพ Autonomous Agent
- ๐ Autoregressive Model
- ๐ถ Autoscaling
- โ Average Pooling
- ๐ Average Precision
- ๐ฆ Avro
- ๐งช Ax Platform
- ๐๏ธ Azure Data Factory
- ๐งช Azure Databricks
- โ๏ธ Azure Machine Learning
- โ๏ธ Azure OpenAI Service
- ๐ค BART
- ๐ค BERT
- ๐ฌ BERTScore
- ๐ข BF16
- ๐งช BIG-bench
- ๐ BLEU
- ๐ค BLEU Score
- ๐ง BRIEF
- ๐ธ BRISK
- ๐ณ๏ธ Backdoor Attack
- โฉ๏ธ Backfill
- ๐ก๏ธ Backpressure
- ๐ Backpropagation
- โณ Backpropagation Through Time
- ๐งบ Bagging
- โ๏ธ Balanced Accuracy
- ๐ฐ Bandit Algorithms
- ๐ฆ Batch
- ๐ Batch Gradient Descent
- ๐ฆ Batch Inference
- ๐งช Batch Normalization
- ๐ฆ Batch Processing
- ๐ข Batch Size
- ๐ฆ Batching
- ๐ฒ Bayesian Inference
- ๐ Bayesian Information Criterion
- ๐ง Bayesian Network
- ๐ฒ Bayesian Neural Network
- ๐ฐ๏ธ Bayesian Optimization
- ๐ฒ Bayesian Statistics
- ๐ญ Beam Search
- ๐ฒ Beautiful Soup
- ๐ Bellman Equation
- ๐ Benchmarking
- ๐ฑ BentoML
- ๐ Berkeley Function-Calling Leaderboard
- ๐ Best-of-N Sampling
- โ Bias
- โ๏ธ Bias & Fairness
- โ Bias (Mathematical)
- โ๏ธ Bias Mitigation
- โ๏ธ Bias and Fairness
- โ๏ธ Bias-Variance Tradeoff
- ๐ง BigQuery
- 0๏ธโฃ1๏ธโฃ Binary Classification
- ๐ฏ Binary Cross-Entropy
- 1๏ธโฃ Binary Encoding
- ๐งฎ BitsAndBytes
- ๐ณ๏ธ Black-box Model
- ๐ค Blending
- ๐งน Bloom Filter
- ๐ฆ Blue-Green Deployment
- ๐ฏ BoTorch
- ๐ฅ Boltzmann Machine
- ๐ Boosting
- ๐ป Bottleneck
- ๐ฒ Bounding Box
- ๐ณ Breadth-First Search
- ๐ Brier Score
- ๐ Broadcasting
- ๐งฎ BroydenโFletcherโGoldfarbโShanno Algorithm
- ๐ชฃ Bucketization
- ๐ฅ Burn-in
- ๐ก Byte Pair Encoding
- ๐งท Byte-Level Tokenization
- ๐งน C4 Dataset
- ๐ณ C4.5 Algorithm
- ๐ CI-CD
- ๐ CIDEr
- ๐ผ๏ธ CIFAR-10
- ๐งฒ CLIP
- ๐ฆ COCO
- ๐ผ๏ธ COCO Dataset
- ๐ฅ๏ธ CPU
- ๐ฆ CRI-O
- ๐ฑ๏ธ CTR Prediction
- โก CUDA
- ๐ฏ Calibration
- ๐ Calibration Curve
- ๐ฏ Calibration Data
- ๐ค Canary Release
- ๐ฏ Candidate Generation
- ๐ผ๏ธ Captioning
- ๐ฏ CarliniโWagner Attack
- ๐๏ธ Case-Based Reasoning
- ๐ฑ CatBoost
- ๐ง Catastrophic Forgetting
- ๐ฒ Categorical Distribution
- ๐ Causal Consistency
- ๐ง Causal Language Model
- ๐ก๏ธ Causal Masking
- ๐งญ Causality
- ๐ก๏ธ Certified Robustness
- ๐ Chain Rule
- ๐ช Chain-of-Thought
- ๐ง Chain-of-Thought Prompting
- ๐ Change Data Capture
- ๐ Change Point Detection
- ๐ Change Request Process
- ๐ฌ ChatGPT
- ๐ฌ Chatbot
- ๐งฉ Checkpointing
- ๐ฆ Chunking
- ๐ Circuit Breaker Pattern
- โ๏ธ Class Imbalance
- ๐ท๏ธ Classification
- โ๏ธ Classification Threshold
- ๐ฒ Classification and Regression Trees
- ๐ก๏ธ Claude
- ๐ค Claude 3
- ๐ค Claude 3.5 Sonnet
- ๐งฐ ClearML
- ๐ Closed-book Question Answering
- ๐๏ธ Code Repository
- ๐ Code Review
- ๐ข Cohere
- ๐ค Collaborative Filtering
- ๐งฎ Combinatorial Optimization
- ๐ Comet ML
- ๐ค Command R+
- ๐งท Commit
- ๐ฅ Committee Machine
- โ Compliance as Code
- ๐งฎ Compressed Sparse Column
- ๐ Compressed Sparse Row
- ๐๏ธ Compression
- โ๏ธ Computational Governance
- ๐งฎ Computational Nodes
- ๐งฎ Compute Optimal
- ๐ Compute Scaling
- โ๏ธ Compute-Optimal Training
- ๐๏ธ Computer Vision
- ๐ Concept Drift
- ๐ Concurrency
- ๐ Conditional Computation
- ๐ฒ Conditional Probability
- ๐ Conditional Random Field
- โ Confidence
- ๐ฏ Confidence Percentage
- ๐ Confidential Computing
- ๐ข Confusion Matrix
- ๐งฎ Conjugate Gradient
- ๐ฃ๏ธ Connectionist Temporal Classification
- ๐ค Consensus Algorithm
- โ๏ธ Consistency
- ๐งช Consistency Checking
- ๐งฉ Consistency Regularization
- ๐งฉ Constituency Parsing
- ๐งฉ Constraint Programming
- ๐งญ Container Orchestration
- ๐๏ธ Container Orchestrator
- ๐ท๏ธ Container Registry
- ๐ฆ Containerization
- ๐ฆ Containers
- ๐งฉ Content-Based Filtering
- ๐ง Context Window
- ๐ฏ Contextual Bandits
- ๐ค Contextual Embeddings
- โพ๏ธ Continual Learning
- ๐งฉ Continuous Bag-of-Words
- ๐ Continuous Delivery
- ๐ Continuous Deployment
- ๐ Continuous Distribution
- ๐ Continuous Integration
- ๐ฒ Continuous Random Variable
- โป๏ธ Continuous Training
- ๐งฒ Contrastive Learning
- ๐๏ธ Contrastive Search
- ๐งฉ ControlNet
- ๐งช Controlled Change Principle
- ๐ฏ Convergence
- ๐ Convex Function
- ๐ Convex Optimization
- ๐ผ๏ธ Convolutional Neural Network
- ๐ฏ Coordinate Descent
- ๐ Cortex
- ๐ Cosine Distance
- โ๏ธ Cost-Complexity Pruning
- โ๏ธ Cost-Sensitive Learning
- ๐ Count-Min Sketch
- ๐ Counterfactual Explanations
- ๐ Counterfactual Fairness
- ๐ Covariate Shift
- ๐ฏ Credit Assignment
- ๐ Cross-Attention
- ๐ Cross-Entropy
- ๐ Cross-Entropy Loss
- ๐งฉ Cross-Modal Alignment
- ๐งช Cross-Validation
- ๐ Curriculum Learning
- ๐ CycleGAN
- ๐งฉ DBSCAN
- ๐ฏ DDPG
- ๐งฉ DSPy
- ๐ ๏ธ Dagster
- ๐งฉ Dask
- ๐ Data Anomalies
- ๐ Data Anomaly Detection
- ๐งฌ Data Augmentation
- โ๏ธ Data Balancing
- ๐ Data Change Activity Metrics
- ๐ Data Contracts
- โฑ๏ธ Data Currency
- ๐ Data Drift
- ๐ Data Drift Detection
- ๐ ๏ธ Data Engineering
- โฑ๏ธ Data Freshness
- ๐ฅ Data Ingestion
- ๐งญ Data Lineage
- ๐ Data Monitoring
- ๐ซฅ Data Obfuscation
- ๐งญ Data Orchestration
- โ๏ธ Data Parallelism
- โก๏ธ Data Pipeline
- ๐งฑ Data Platform
- ๐งผ Data Preprocessing
- โป๏ธ Data Product Lifecycle
- ๐ชช Data Pseudonymization
- ๐ก๏ธ Data Quality Gates
- โ๏ธ Data Race
- ๐ฌ Data Science
- ๐ Data Science Lifecycle
- ๐ Data Streaming
- ๐ง Data Transformation
- ๐งญ Data Understanding
- โ๏ธ Data Validation
- โก Data Velocity
- ๐๏ธ Data Version Control
- ๐๏ธ Data Versioning
- ๐ช๏ธ Data Volatility
- โ๏ธ DataOps
- ๐ฅ Databricks
- ๐งฑ Databricks Lakehouse Platform
- ๐ค Databricks Machine Learning
- โ๏ธ Dataset Shift
- ๐๏ธ Dead Letter Queue
- ๐ Debezium
- ๐ Debugging
- ๐ต๏ธโโ๏ธ Deception
- ๐งญ Decision Boundary
- ๐ฒ Decision Forest
- ๐ณ Decision Tree
- ๐ Declarative Governance
- ๐งฉ Decoder
- ๐ฃ๏ธ Decoding
- ๐ง Decoding Strategies
- ๐ง Deep Learning
- ๐ง Deep Neural Network
- ๐น๏ธ Deep Q-Network
- ๐๏ธ DeepSeek
- ๐ค DeepSeek V3.1
- โก DeepSpeed
- ๐ถ DeepWalk
- ๐งช Deequ
- ๐ก๏ธ Defensive Distillation
- ๐งฉ Deliberate Reasoning
- ฮ Delta Lake
- ๐ Delta Live Tables
- ๐ Demographic Parity
- ๐ Denoising
- ๐ซ๏ธ Denoising Diffusion Probabilistic Model
- ๐ง Dense Transformer
- ๐ Dense Vector
- ๐งฌ DenseNet
- ๐ณ Dependency Parsing
- ๐ Deployment Pipeline
- ๐งฉ Depthwise Separable Convolution
- ๐ค Detokenization
- ๐ Detrending
- ๐งฉ Dice Coefficient
- ๐ Differential Privacy
- ๐จ Diffusers Library
- ๐ซ๏ธ Diffusion Models
- ๐ป Dimensionality Reduction
- ๐ฏ Direct Preference Optimization
- ๐งญ Directional Derivative
- ๐ก๏ธ Disaster Recovery
- ๐ฆ Discretization
- ๐งช Discriminator
- ๐ง Distant Supervision
- โ๏ธ DistilBERT
- ๐งช Distillation
- ๐ฅ๏ธ Distributed Training
- ๐ Distribution Shift
- ๐งฉ Distribution-based Clustering
- ๐ณ Docker
- ๐ณ Docker Compose
- ๐ Document AI
- ๐ Domain Adaptation
- ๐งญ Domain Generalization
- ๐ Domain Invariant Features
- ๐ Domain Shift
- โ Dot Product
- ๐ Double Descent
- ๐ป Downsampling
- ๐ค Dreamer
- ๐ Drift Detection
- ๐ชฃ Dropout
- ๐งฉ Dynamic Programming
- ๐ง Dynamic Quantization
- ๐งฉ ELMo
- ๐ ELU
- โน๏ธ Early Stopping
- ๐ฑ Edge AI
- ๐ Edge Deployment
- โ๏ธ EfficientNet
- โ๏ธ Elastic Net
- ๐ค EleutherAI
- ๐งญ Embedding Space
- ๐งฉ Embeddings
- ๐ Empirical Distribution
- โ๏ธ Empirical Risk Minimization
- ๐งฐ Encapsulation
- ๐ฆ Encoder
- ๐ Encoder-Decoder
- ๐ Encoder-Decoder Architecture
- โ End-to-End Testing
- ๐งฎ Ensemble Learning
- โก๏ธ Entailment
- ๐ฒ Entropy Regularization
- ๐งช Environment
- โฑ๏ธ Epoch
- ฮต Epsilon
- ๐ฒ Epsilon-Greedy
- ๐งฎ Equalized Odds
- ๐ Error Analysis
- ๐ Error Rate
- ๐ Evaluation
- ๐งช Evaluation Harness
- ๐ Evaluation Metrics
- ๐ญ Evasion Attack
- ๐ Event Log
- ๐ Event Stream
- ๐ก Event Streaming
- โฑ๏ธ Event Time
- โณ Eventual Consistency
- ๐ Evidence Lower Bound
- ๐งฌ Evolution Strategies
- ๐ ExLlama
- ๐ฆ Exactly-Once Delivery
- โ Exactly-Once Processing
- โ Exactly-Once Semantics
- ๐ Expected Calibration Error
- โป๏ธ Experience Replay
- ๐งช Experiment Tracking
- ๐ง Expert Network
- ๐ค Expert System
- ๐ Explainability
- ๐งญ Explainability Dashboard
- ๐ฅ Exploding Gradient
- โ๏ธ Exploration-Exploitation
- โ๏ธ Exploration-Exploitation Tradeoff
- ๐ Exponential Backoff
- ๐ Exponential Loss
- ๐ก Extended Kalman Filter
- ๐ F-beta Score
- ๐ฏ F1 Score
- ๐งฐ FAISS
- โ ๏ธ FGSM
- ๐ผ๏ธ FLUX.1.1 Pro
- ๐ข FP16
- ๐ง FPGA
- โ๏ธ Fairness
- โ๏ธ Fairness Metrics
- ๐ง Fairseq
- ๐ False Negative
- ๐ False Negative Rate
- โ ๏ธ False Positive
- โ ๏ธ False Positive Rate
- ๐ช FastAPI ML
- ๐ค FastText
- ๐ฏ Faster R-CNN
- ๐ FasterTransformer
- ๐งฉ Feast
- ๐ข Feature
- ๐ Feature Drift
- ๐ Feature Extraction
- ๐ฆ Feature Flags
- ๏ธโฃ Feature Hashing
- ๐ฏ Feature Importance
- ๐บ๏ธ Feature Map
- ๐ง Feature Pipeline
- ๐ผ๏ธ Feature Pyramid Network
- ๐ป Feature Reduction
- ๐ Feature Registry
- ๐ Feature Scaling
- โ Feature Selection
- ๐งฉ Feature Store
- ๐ค Federated Learning
- โก๏ธ Feed-Forward Network
- ๐ Feedback Loop
- ๐ง Few-Shot Learning
- ๐งฉ Few-shot Prompting
- ๐ ๏ธ Fine-Tuning
- โก Fireworks AI
- ๐ Fisher Information
- โ๏ธ FlashAttention
- ๐ง FlexAttention
- โก๏ธ Flow
- ๐ Flow Variable
- ๐ฏ Focal Loss
- ๐ Forecasting
- โ๏ธ Formal Verification
- ๐งฑ Foundation Model
- ๐ถ Fourier Transform
- ๐ Frequency Encoding
- ๐ Frontier Model
- ๐ ๏ธ Full Fine-Tuning
- ๐ง Fully Convolutional Network
- ๐ Function Calling
- ๐ญ GAN
- โ๏ธ GCP AI Platform
- ๐พ GGUF
- ๐ผ๏ธ GLM-4.5V
- ๐งช GLUE
- ๐งฉ GPQA
- ๐ง GPT
- ๐งฉ GPT-3
- ๐ฌ GPT-3.5
- ๐ GPT-4
- ๐๏ธ GPT-4o
- ๐ GPT-5
- ๐ค GPT-5.0
- ๐งฎ GPTQ
- ๐งฎ GPTQ Quantization
- ๐ฎ GPU
- ๐๏ธ GPU Inference
- ๐ GPU Utilization
- ๐ GRU
- ๐งฉ GSM8K
- ๐ฆ Gating Network
- ๐ Gaussian Mixture Model
- ๐ Gaussian Processes
- ๐ท Gemini
- ๐ง Gemini 3 Pro
- ๐ชถ Gemma 3
- โ General Availability
- ๐ฏ Generalization Error
- ๐ค Generative AI
- ๐จ Generative Model
- ๐จ Generative Modeling
- ๐๏ธ Generator
- ๐ฎ Genie 3
- ๐ข Geohash
- ๐ณ Gini Impurity
- ๐ฟ Git
- ๐๏ธ Git Large File Storage
- ๐ง GitOps
- ๐ง Global Average Pooling
- ๐ฏ Global Optimization
- ๐ Glow
- ๐ Goodness of Fit
- ๐๏ธ Google Cloud Bigtable
- โก Google Cloud Functions
- ๐ฃ Google Cloud Pub-Sub
- ๐ Google Colab
- ๐ค Google DeepMind
- ๐ท Google Vertex AI
- ๐ก๏ธ Governance as Code
- โ Gradient
- โ Gradient Accumulation
- ๐ฒ Gradient Boosting
- ๐งฎ Gradient Checkpointing
- ๐ Gradient Leakage
- ๐ Grafana
- ๐ง Graph Attention Network
- ๐ง Graph Convolutional Network
- ๐ธ๏ธ Graph Embedding
- ๐ง Graph Neural Network
- ๐งฉ Graph Partitioning
- ๐ธ๏ธ GraphSAGE
- ๐ฎ Graphics Processing Unit
- ๐ฎ Graphics Processing Unit Acceleration
- โก Greedy Decoding
- โป๏ธ Green AI
- ๐งฎ Grid Search
- ๐ง Grokked Transformer
- ๐งช Group Normalization
- ๐ฏ Grouped Query Attention
- ๐ก๏ธ Guardrails
- ๐งญ Guidance
- โฌก H3
- โ๏ธ HELM
- ๐ HMAC
- ๐ธ๏ธ HNSW
- ๐ HOG
- ๐ฅ HTTP 500
- ๐ฒ Hamiltonian Monte Carlo
- ๐งฉ Hashing Trick
- ๐งฐ Haystack
- ๐ง He Initialization
- ๐งฎ Hessian
- ๐งญ Heuristic Search
- ๐ HiFi-GAN
- ๐ง Hidden Layer
- ๐ Hidden Markov Model
- ๐ณ Hierarchical Softmax
- ๐ก๏ธ High Availability and Disaster Recovery
- ๐ข High Cardinality
- ๐งฑ Hinge Loss
- ๐ฐ๏ธ Historical Versions
- ๐งช Holdout Sample
- ๐งฐ Holdout Set
- ๐ Homomorphic Encryption
- ๐ง Horovod
- โ๏ธ Huber Loss
- ๐ค Hugging Face
- ๐๏ธ Hugging Face Hub
- ๐ค Hugging Face Transformers
- ๐งโโ๏ธ Human Evaluation
- ๐งโโ๏ธ Human Oversight
- ๐งโโ๏ธ Human-in-the-Loop
- ๐งช HumanEval
- ๐๏ธ Hybrid Recommender
- ๐๏ธ Hyperband
- ๐ฏ Hyperopt
- โ๏ธ Hyperparameter
- ๐๏ธ Hyperparameter Tuning
- ๐ง Hypothesis Space
- ๐งพ ICD-10 Codes
- ๐ IFEval
- ๐งฎ INT4
- ๐ฆ INT8
- โ๏ธ ISO-IEC 23894
- ๐งญ ISO-IEC 42001
- ๐ฏ IVF-PQ
- ๐ Idempotency
- โป๏ธ Idempotent Request
- ๐ฏ Identification
- ๐ Identity
- ๐ท๏ธ Image Annotation
- ๐ผ๏ธ Image Captioning
- ๐ผ๏ธ Image Classification
- ๐ผ๏ธ Image Generation
- ๐ผ๏ธ Image Processing
- ๐ Image Recognition
- ๐จ Image Synthesis
- ๐ Image-to-Image Translation
- ๐ Image-to-Text
- ๐ผ๏ธ ImageNet
- ๐ผ๏ธ Imagen 3
- โ๏ธ Imbalanced Data
- ๐ Implement Data Sharing-Integration Services
- ๐ฃ Implicit Feedback
- ๐ฏ Importance Sampling
- ๐ง In-Context Heads
- ๐ง In-Context Learning
- ๐ฟ Inception
- ๐จ Incident Management
- ๐ Individual Conditional Expectation
- ๐ Induction Heads
- ๐ Inductive Transfer Learning
- โก Inference
- โ๏ธ Inference Engine
- ๐ Inference Optimization
- ๐ InfluxDB
- ๐ Information Gain
- ๐ Information Retrieval
- ๐๏ธ Infrastructure as Code
- ๐ง Initialization
- ๐ผ๏ธ Inpainting
- ๐จ Instance Normalization
- โ๏ธ Instance Segmentation
- ๐งญ Instruction Following
- ๐ Instruction Tuning
- ๐งฉ Instructor
- ๐งญ Integrated Gradients
- ๐ Integration Testing
- ๐ฅ๏ธ Intel
- ๐ Inter-annotator Agreement
- ๐ Interpretability
- ๐ช Intersection over Union
- โ๏ธ Inverse Probability Weighting
- ๐ฏ Inverse Reinforcement Learning
- ๐๏ธ Inverted File Index
- ๐ฒ Isolation Forest
- ๐บ๏ธ Isomap
- ๐งฎ Isotonic Regression
- ๐ Iteration
- โก JAX
- ๐งพ JSON
- ๐งฑ JSONFormer
- ๐ Jacobian
- ๐งญ Jaeger
- ๐ Jailbreak
- ๐ถ Jitter
- ๐ Joint Embedding
- โก Julia
- ๐ Jupyter Notebook
- ๐ K-Fold Cross-Validation
- ๐ณ KD-Tree
- โธ๏ธ KServe
- ๐๏ธ KV Cache
- ๐งต Kafka Streams
- ๐ก Kalman Filter
- ๐ Kaplan Scaling Laws
- โ KarushโKuhnโTucker Conditions
- ๐ง Keras
- ๐งฎ Kernel
- ๐ง Kernel Methods
- โ๏ธ Kernel SVM
- ๐ช Kernel Trick
- ๐งฉ Key Derivation Function
- ๐ค Kimi K2
- โ๏ธ Knowledge Distillation
- โ๏ธ Kubeflow
- ๐ Kubeflow Pipelines
- โธ๏ธ Kubernetes
- โฐ Kubernetes CronJob
- ๐ KullbackโLeibler Divergence
- ๐ฏ L-BFGS
- ๐ L1 Loss
- ๐ L1 Regularization
- ๐ L2 Regularization
- ๐งฉ LAION-5B
- ๐ LIME
- ๐ธ๏ธ LINE
- ๐งช LLM Evaluation
- โ๏ธ LLM Inference
- ๐ง LLM Training
- ๐ฆ LLaMA
- ๐ฆ LLaMA 3
- ๐๏ธโ๐จ๏ธ LLaMA 3.2 Vision
- ๐ฆ LLaMA 4 Maverick
- โ๏ธ LMSYS Chatbot Arena
- ๐ LSTM
- ๐ท๏ธ Label
- ๐ซ Label Leakage
- ๐งช Label Noise
- โ๏ธ Label Shift
- ๐ฏ Label Smoothing
- ๐ท๏ธ Labeled Data
- โ๏ธ Labeling
- ๐ Lagrange Multipliers
- ๐งฉ LangChain
- ๐ฃ๏ธ Language Model
- ๐ฃ๏ธ Language Modeling
- ๐ค Large Language Model
- ๐ชข Lasso
- โณ Late Data
- ๐ฐ๏ธ Late Data Handling
- โฑ๏ธ Latency
- โฑ๏ธ Latency Optimization
- ๐ Latent Diffusion
- ๐จ Latent Diffusion Model
- ๐ Latent Space
- ๐งฑ Layer
- โ๏ธ Layer Normalization
- ๐ Leaderboards
- โก Leaky ReLU
- ๐ Learning Curve
- ๐๏ธ Learning Rate
- ๐ Learning Rate Schedule
- ๐ Learning Rate Scheduler
- ๐ก LightGBM
- ๐ฏ Likelihood
- ๐งญ Line Search
- ๐งญ Lineage
- ๐ Linear Classifier
- ๐ Linear Model
- ๐งฎ Linear Programming
- ๐ฎ Link Prediction
- ๐ฆ Llama 2
- ๐ฆ LlamaIndex
- ๐งฉ LoRA
- ๐ฆ Load Shedding
- โฐ๏ธ Local Optima
- ๐งญ Local Optimum
- ๐งญ Local Outlier Factor
- ๐งญ Locality-Sensitive Hashing
- ๐งฎ Log Loss
- ๐งฎ Log-Likelihood
- ๐ Logging
- ๐ข Logistic Regression
- โ Logit
- ๐ Long Context
- ๐ Loss Function
- โฐ๏ธ Loss Landscape
- โ๏ธ Loss Scaling
- โก Low Latency
- ๐ Low-Rank Approximation
- โ MAC
- ๐งฎ MATH Dataset
- ๐ METEOR
- ๐ค MLCommons
- ๐ MLOps
- ๐ MLPerf
- ๐ง MLServer
- ๐ MLflow
- ๐ง MMLU
- ๐ข MNIST
- ๐งช MT-Bench
- ๐ค Machine Learning
- ๐ค Machine Learning Engineer
- โ๏ธ Macro-Average
- ๐ง Magistral Small
- ๐งฐ Maintainability
- ๐๏ธ Manufacturing Execution Systems
- ๐บ๏ธ Marble
- ๐ก๏ธ Margin of Safety
- ๐งญ Markov Decision Process
- ๐ธ๏ธ Markov Random Field
- ๐ญ Mask R-CNN
- ๐งฉ Masked Language Model
- ๐ญ Masked Language Modeling
- ๐ Matthews Correlation Coefficient
- ๐ Max Pooling
- ๐ฏ Maximum Likelihood
- ๐ Maximum Likelihood Estimator
- ๐ Mean Absolute Error
- ๐ Mean Absolute Percentage Error
- ๐ฉน Mean Imputation
- ๐งฎ Mean Squared Error
- ๐ Medallion Architecture
- ๐ Median Absolute Deviation
- ๐ฉน Median Imputation
- ๐งฑ Megatron-LM
- ๐ต Mel-Frequency Cepstral Coefficients
- ๐ถ๏ธ Membership Inference
- ๐ต๏ธ Membership Inference Attack
- ๐ถ Memory Bandwidth
- ๐ฆ Memory Footprint
- ๐ง Memory Optimization
- ๐ Merge Request
- ๐ฒ Mersenne Twister
- ๐ Message Passing
- ๐ฆ MessagePack
- ๐ง Meta-Learning
- ๐งญ Metaflow
- ๐ Metric Learning
- โฑ๏ธ Micro Batch Processing
- ๐ Micro-Average
- โฑ๏ธ Micro-batching
- ๐งต Microsoft Fabric
- ๐๏ธ Milvus
- ๐งฉ MinHash
- ๐งช Mini-Batch
- ๐ Mini-batch Gradient Descent
- ๐ต Minimum Points
- ๐ Mish
- โ Missing Data
- ๐ฌ๏ธ Mistral 7B
- ๐ฌ๏ธ Mistral AI
- โ๏ธ Mistral Medium 3
- ๐ก๏ธ Mitigation
- โ๏ธ Mixed Precision
- โ๏ธ Mixed Precision Training
- ๐ง Mixtral 8x7B
- ๐งฉ Mixture of Experts
- ๐งช Mixup
- ๐ฑ MobileNet
- โ๏ธ Modal
- ๐ค Model
- ๐ Model Averaging
- ๐ง Model Capacity
- ๐ Model Cards
- ๐งฉ Model Complexity
- ๐ง Model Compression
- ๐ Model Context Protocol
- ๐ Model Deployment
- ๐ Model Evaluation
- ๐ Model Explainability
- ๐ Model Fingerprinting
- ๐ฑ Model Garden
- ๐ฏ Model Generalization
- โ๏ธ Model Governance
- ๐๏ธ Model Hub
- ๐ Model Inversion
- ๐ Model Monitoring
- โ ๏ธ Model Overfitting
- ๐ Model Provenance
- โ๏ธ Model Pruning
- โ๏ธ Model Quantization
- ๐๏ธ Model Registry
- ๐ก๏ธ Model Robustness
- ๐งญ Model Router
- โ๏ธ Model Serving
- ๐ฆ Model Size
- ๐ต๏ธ Model Stealing
- ๐ Model Transparency
- ๐ชซ Model Underfitting
- ๐๏ธ Model Versioning
- โ๏ธ Model Weights
- ๐ง Model-Based Reinforcement Learning
- ๐งฉ Modularity
- ๐โโ๏ธ Momentum
- ๐ก Monitor Data Movement
- ๐ Monitoring
- ๐ฒ Monte Carlo
- ๐ฒ Monte Carlo Methods
- ๐ณ Monte Carlo Tree Search
- โ๏ธ MuZero
- ๐ฅ Multi-Agent System
- ๐ง Multi-Head Attention
- ๐ Multi-Region Replication
- ๐งฎ Multi-Task Learning
- ๐ฐ Multi-armed Bandit
- ๐ท๏ธ Multi-label Classification
- ๐งฉ Multiclass Classification
- ๐ง Multilayer Perceptron
- ๐ Multilingual Model
- ๐๏ธ Multimodal
- ๐ฏ Multimodal Embeddings
- ๐ง Multimodal LLM
- ๐ผ๏ธ Multimodal Learning
- ๐งฉ Multimodal Model
- โป๏ธ Multiple Imputation
- โน๏ธ Mutual Information
- ๐ NIST AI Risk Management Framework
- ๐ง NPU
- ๐ฅ๏ธ NVIDIA
- โก NVIDIA H100
- โก NVIDIA TensorRT
- โก Nadam
- ๐จ Naive Bayes
- ๐ท๏ธ Named Entity Recognition
- ๐ฃ๏ธ Natural Language Processing
- ๐ Natural Language Understanding
- โฑ๏ธ Near Real-time
- ๐ฏ Nearest Neighbor
- ๐ Negative Log-Likelihood
- ๐ฒ Negative Sampling
- ๐ฆ Neptune.ai
- ๐๏ธ Nesterov Momentum
- ๐ธ๏ธ Network Partition
- ๐ Neural Architecture Search
- ๐ง Neural Language Model
- ๐ง Neural Network
- ๐ Neural Processing Unit (NPU)
- ๐ Neural Scaling Law
- ๐ฃ๏ธ Neural TTS
- ๐ Neural Vocoder
- ๐งฉ Neuro-Symbolic AI
- ๐ Neuron
- ๐งญ Nevergrad
- ๐งฎ Newtonโs Method
- ๐งฎ Newton-Raphson Method
- ๐ธ๏ธ Node Classification
- ๐งฉ Node2Vec
- ๐ก Noise
- ๐ซ Non-Maximum Suppression
- ๐ Nonconvex Optimization
- โก Nonlinear Activation
- ๐ง Nonlinearity
- ๐ณ Nonparametric Model
- ๐งช Normalization (Statistics)
- ๐ Normalizing Flow
- ๐ Novelty Detection
- ๐งช Nucleus Sampling
- ๐ฆ NumPy
- ๐งฎ NumPy Array
- ๐ฏ Numeric Precision
- ๐ Numeric Prediction
- โซ Numerical Integration
- ๐งน OCR Post-Processing
- โ๏ธ OECD AI Principles
- ๐ ONNX
- ๐ ONNX Runtime
- ๐งญ OPTICS
- ๐ ORB
- ๐ Object Detection
- ๐ฏ Objective Function
- ๐ญ Observability
- ๐ Off-Policy Learning
- ๐๏ธ Offline Feature Store
- ๐ฏ On-Policy Learning
- ๐ฐ๏ธ One-Class SVM
- ๐ข One-Hot Encoding
- ๐ฏ One-shot Learning
- โ๏ธ One-vs-One
- โก Online Feature Store
- โก Online Inference
- ๐ Online Learning
- ๐ Open Evaluation
- ๐ Open LLM
- ๐ Open LLM Leaderboard
- ๐ Open Model Leaderboard
- ๐ Open Model Spec
- ๐งฉ Open Source AI
- ๐งญ Open Source Embeddings
- โ๏ธ Open Weight Model
- โ๏ธ Open Weights
- โจ Open-Ended Generation
- ๐ค OpenAI
- ๐ค OpenAI API
- ๐ง OpenAI o3
- ๐ OpenAPI
- ๐๏ธ OpenCV
- ๐งญ OpenLineage
- ๐๏ธ OpenMetadata
- ๐ก OpenTelemetry
- ๐งญ OpenTracing
- ๐๏ธ OpenVINO
- ๐ค OpenVINO Toolkit
- โ Operational Consistency
- โฑ๏ธ Operational Dashboard
- ๐ Operational Metadata
- ๐ Optimal Solution
- ๐๏ธ Optimization
- โ๏ธ Optimization Algorithm
- โ๏ธ Optimizer
- ๐ฏ Optuna
- ๐งฉ Orchestration
- ๐ Out-of-Bag Error
- ๐๏ธ Out-of-Core Learning
- ๐ง Out-of-Distribution
- ๐ Out-of-Distribution Detection
- ๐ Out-of-Distribution Generalization
- ๐ Out-of-Order Events
- ๐ค Out-of-Vocabulary
- ๐ Outliers
- ๐งฉ Outlines
- ๐ฏ Output Layer
- ๐ฏ Output Variable
- ๐ง Overfitting
- โ๏ธ Overhead
- โ๏ธ Oversampling
- ๐ง Overthinking
- ๐ฆ PEFT Library
- ๐งฎ PGD
- ๐ PHI
- ๐ฏ PPO
- ๐ PR AUC
- ๐งญ PROV-O
- ๐ฆ Package Management
- ๐๏ธ Package Registry
- ๐งฉ Panoptic Segmentation
- ๐ Papers with Code
- โก Parallel Processing
- ๐งฉ Parameter-Efficient Fine-Tuning
- ๐ข Parameterized Model
- โ๏ธ Parameters
- ๐ท๏ธ Part-of-Speech Tagging
- ๐ Partial Autocorrelation
- ๐ Partial Dependence
- ๐ Partial Dependence Plot
- ๐ฆ Particle Swarm Optimization
- ๐ผ๏ธ Pascal VOC
- โ๏ธ Penalty Term
- ๐๏ธ Perception
- ๐ง Perceptron
- โ๏ธ Performance Tuning
- ๐ฒ Permutation Test
- ๐ฒ Permuted Congruential Generator
- ๐ Perplexity
- ๐ Phi-3
- โก Phi-4
- โก Phi-4 Mini
- ๐ค Phi-4 Mini Instruct
- ๐ฒ Pinecone
- ๐ ๏ธ Pipeline Orchestration
- ๐ฆ Pipeline Parallelism
- ๐ Pipelines
- ๐ผ๏ธ Pixtral Large
- ๐ Platt Scaling
- ๐ณ Podman
- ๐งฎ Poisson Data
- ๐ข Poisson Loss
- ๐ Policy
- ๐ Policy Gradient
- ๐ Policy Gradient Theorem
- ๐ฏ Policy Optimization
- โ๏ธ Policy as Code
- ๐ป Pooling
- ๐งฑ Pooling Layer
- ๐งฌ Population Based Training
- ๐ Positional Encoding
- โ Positive Class
- โ๏ธ Post-Training Quantization
- ๐ ๏ธ Post-processing
- ๐ฏ Posterior
- ๐ Postmortem
- ๐ฏ Precision
- ๐งฎ Precision Matrix
- ๐ฏ Precision and Recall
- ๐ Precision-Recall AUC
- ๐ Precision-Recall Curve
- ๐ฏ Prediction
- โ๏ธ Prediction Bias
- ๐ Prediction Error
- ๐ค Predictive Model
- โ๏ธ Predictive Parity
- ๐งญ Prefect
- ๐ง Preference Learning
- ๐งฉ Prefix Tuning
- ๐งผ Preprocessing
- ๐ฆ Pretrained Model
- ๐ Pretraining
- ๐งฎ Privacy Budget
- ๐ก๏ธ Privacy-Preserving
- ๐ Probabilistic Graphical Model
- ๐๏ธ Probabilistic Model
- ๐ Probability Density Function
- ๐ฏ Probability Mass Function
- ๐ Probably Approximately Correct Learning
- ๐งพ Processing Log Analysis
- ๐ Processing Time
- ๐ฆ Product Quantization
- ๐ค Program Synthesis
- ๐ Progressive Delivery
- ๐ Prometheus
- โ๏ธ Prompt Engineering
- ๐ฏ Prompt Tuning
- ๐ฃ๏ธ Prompting
- ๐ Propagation
- ๐ฎ Prophet
- ๐๏ธ Prosody
- ๐ Protocol Buffers
- ๐ง Prototypical Networks
- ๐ณ Pruning
- ๐ง Pseudo-Labeling
- ๐ต๏ธโโ๏ธ Pseudonymization
- ๐ฆ Puffin
- ๐ Pull Request
- ๐ฅ PyTorch
- ๐งฉ PyTorch Distributed
- โ Pydantic
- ๐ Python
- ๐งญ Q-Learning
- ๐งฎ QLoRA
- ๐ข QuIP
- ๐งช Quality Assurance
- ๐ Quantile Binning
- โ๏ธ Quantization
- ๐๏ธ Quantization-Aware Training
- โ๏ธ Quasi-Newton Method
- ๐ฏ Query-Key-Value
- โ Question Answering
- โณ Queueing Theory
- ๐งฟ Qwen2.5-VL-72B
- ๐ Qwen3
- ๐งฉ R-CNN
- ๐ R-squared
- ๐งฉ R1
- ๐งช R2 Score
- ๐ฎ REINFORCE
- ๐ค RLAIF
- ๐ค RLHF
- ๐ RMSE
- โ๏ธ RMSProp
- ๐ ROC AUC
- ๐ ROC Curve
- โ๏ธ ROCm
- ๐ ROUGE
- ๐งฎ ROUGE Score
- ๐ฃ Raft
- ๐ฒ Random Forest
- ๐ฒ Random Projection
- ๐ฒ Random Search
- ๐ Rank-Based Feature
- ๐ฆ Rate Limiting
- ๐ฅ Raw Data
- ๐ Ray
- ๐ฐ๏ธ Ray Serve
- ๐ Ray Tune
- ๐ค ReAct
- โก ReLU
- ๐ Read-Your-Writes Consistency
- โก Real-Time
- โก Real-Time Governance
- โก Real-time Analytics
- โก Real-time Data
- โก Real-time Inference
- ๐ RealNVP
- ๐ง Reasoning Models
- ๐ฏ Recall
- ๐ Recommender System
- โฑ๏ธ Recovery Point Objective
- โณ Recovery Time Objective
- ๐ Recurrent Neural Network
- ๐ก๏ธ Red Teaming
- ๐งต RedPajama
- โก Redis
- โ๏ธ Reduced Error Pruning
- ๐ ๏ธ Refactoring
- ๐ฎ Reinforcement Learning
- ๐ก๏ธ Reliability
- ๐ Reparameterization Trick
- ๐ Repetition Penalty
- ๐ Replicability
- ๐ง Representation Learning
- ๐ Reproduction
- ๐ Reranking
- ๐ง ResNet
- ๐ Residual Analysis
- ๐งฎ Resource Allocation
- ๐ ๏ธ Resource Utilization Protocols
- ๐ค Responsible AI
- ๐ Retraining
- ๐ Retry Policy
- โฉ๏ธ Reversibility
- ๐ Reward Function
- ๐ Reward Model
- ๐งญ Reward Modeling
- ๐งฐ Ridge Regression
- ๐ Risk Minimization
- ๐ง RoBERTa
- ๐ Robust Scaling
- ๐งฑ Robustness
- โฉ๏ธ Rollback
- ๐ Rolling Deployment
- ๐ Rolling Update
- ๐ Rollout
- ๐ต๏ธ Root Cause Analysis
- ๐ Root Mean Squared Logarithmic Error
- ๐ฆ Router LM
- ๐งญ Router Policy
- ๐งฉ Row Level Changes
- ๐งฉ Rule Language
- โ๏ธ Rule-based Reasoning
- ๐ RunPod
- ๐ก๏ธ Rรฉnyi Differential Privacy
- ๐๏ธ SAC
- ๐ SARIMA
- ๐ SARSA
- ๐โโ๏ธ SGD with Momentum
- ๐ SHAP
- ๐งฉ SHAP Values
- ๐ค SLAM
- โ๏ธ SMOTE
- ๐ SQuAD
- ๐ ๏ธ SWE-bench
- ๐งฐ Sacred
- ๐ฆ Safety Filters
- ๐๏ธ Safety Tuning
- ๐งฉ Saga Pattern
- ๐ง SageMaker Feature Store
- ๐บ๏ธ Saliency Map
- โ ๏ธ Sampling Bias
- ๐ง Satisfiability
- ๐ ScaNN
- ๐ท Scala
- ๐ Scalar Quantization
- ๐ฏ Scaled Dot-Product Attention
- ๐ Scaling
- โฑ๏ธ Scheduler
- ๐ Schema Drift
- ๐ก๏ธ Schema Enforcement
- ๐งฉ Schema Evolution
- ๐ Schema Registry
- ๐งฑ Schema Versioning
- ๐งช SciPy
- ๐ฏ Score
- ๐ฏ Scoring Model
- ๐ Search
- ๐งญ Search Engine
- ๐ Search Index
- ๐งญ Search Space
- ๐งฎ Second-Order Optimization
- ๐งท Secrets Management
- ๐ Secure Aggregation
- ๐ Secure Multiparty Computation
- ๐ฒ Seed
- ๐ผ๏ธ Segmentation
- ๐งฉ Seldon Core
- ๐ฏ Selection Bias
- ๐ธ๏ธ Self-Attention
- ๐ Self-Consistency
- ๐ Self-Driving Car
- ๐ ๏ธ Self-Service Data Infrastructure
- ๐ง Self-Supervised Learning
- ๐ Semantic Drift
- ๐ง Semantic Reasoning Engine
- ๐ง Semantic Role Labeling
- ๐ Semantic Search
- ๐งฉ Semantic Segmentation
- ๐ Semantic Similarity
- ๐งช Semi-supervised Learning
- ๐๏ธ Sensitivity Analysis
- ๐ฐ๏ธ Sensor Fusion
- ๐ง Sentence Embedding
- โ๏ธ Sentence Segmentation
- ๐ง Sentence Transformer
- ๐งฉ Sentence-BERT
- โ๏ธ SentencePiece
- ๐ Sequence Model
- โฑ๏ธ Sequence Modeling
- ๐ Sequence-to-Sequence
- โ๏ธ Serverless
- โ๏ธ Serverless Computing
- ๐งฉ Service Account
- ๐ Service Level Indicator
- ๐ฏ Service Level Objective
- ๐ธ๏ธ Service Mesh
- โฑ๏ธ Session Window
- ๐ช Shadow Deployment
- ๐ต๏ธโโ๏ธ Shadow Models
- ๐ Shuffling
- ๐ข Sigmoid Function
- ๐งฉ SimCSE
- ๐ Similarity Metric
- ๐ฏ Similarity Search
- ๐งช Simulation
- ๐ค Sink Data Store
- ๐ Sinusoidal Positional Encoding
- ๐ฃ๏ธ Skip-Gram
- ๐ช Sliding Window
- ๐ง Sliding Window Attention
- ๐งฑ Smart Open-source Middleware
- ๐งฎ Smooth L1 Loss
- ๐ SmoothQuant
- ๐ธ Snapshot Isolation
- โ Soda Core
- ๐ซง Soft Labels
- โ๏ธ Soft Margin
- ๐๏ธ Softmax
- ๐งฎ Softmax Function
- โ Softplus
- ๐งฐ Software Development Kit
- ๐งพ Source Code
- ๐ Source Data Store
- ๐งช Spaces
- ๐ง Spark MLlib
- ๐ Spark Streaming
- โก Spark Structured Streaming
- ๐งฉ Sparse Attention
- ๐ Sparse Representation
- โ๏ธ Sparsify
- 0๏ธโฃ Sparsity
- ๐๏ธ Speaker Identification
- ๐ฏ Specificity
- ๐ธ๏ธ Spectral Clustering
- ๐ Spectral Density
- ๐งญ Spectral Embedding
- โก Speculative Decoding
- ๐๏ธ Speech Recognition
- ๐ฃ๏ธ Speech Synthesis
- ๐ฃ๏ธ Speech-to-Text
- ๐ช Split Learning
- โก๏ธ Spot Instances
- ๐ชถ SqueezeLLM
- ๐ก๏ธ Stability
- ๐ผ๏ธ Stability AI
- ๐จ Stable Diffusion
- ๐งฑ Stacked Generalization
- ๐งฑ Stacking
- ๐งพ Standards as Code
- ๐ฎ State
- ๐ง State Machine Replication
- ๐งญ State Space
- ๐ State Space Model
- ๐ State of the Art
- ๐ง Stateful Processing
- ๐ Static Analysis
- ๐ฑ Stemming
- ๐ฒ Stochastic
- โ๏ธ Stochastic Gradient Descent
- ๐ฒ Stochastic Optimization
- ๐งน Stopword Removal
- ๐ Stream Analytics
- ๐ Streaming
- ๐ง Streaming Data
- โก Streaming Ingestion
- ๐ Streaming Join
- ๐๏ธ Stride
- ๐งฎ Structural Risk Minimization
- ๐งฉ Structured Output
- ๐ Structured Streaming
- ๐จ Style Transfer
- ๐จ StyleGAN
- ๐ Subgradient
- ๐งฑ SubstitutionโPermutation Network
- ๐ค Subword
- ๐ค Subword Tokenization
- ๐ Summarization
- ๐ Super-Resolution
- ๐งฐ SuperGLUE
- ๐ฏ Supervised Fine-Tuning
- ๐ง Supervised Learning
- ๐ Support Vector Machine
- ๐งช Surrogate Model
- ๐ช Swin Transformer
- ๐ Swish
- ๐ Switch Transformer
- ๐ช Sycophancy
- โก Synapse Spark Pool
- ๐งญ System Prompt
- ๐ System for Cross-domain Identity Management
- ๐ง T5
- ๐ TDSP
- ๐ TGI
- โ๏ธ TPU
- ๐งฎ TPU v5
- ๐งฐ TVM
- ใฐ๏ธ Tanh
- โฐ Tanh Function
- ๐ข Target Encoding
- โฐ Task Scheduling
- ๐ฏ Task-Specific Model
- ๐ Teacher Forcing
- ๐ Technology Readiness Level
- ๐งฉ Tecton
- ๐ก๏ธ Temperature
- ๐ก๏ธ Temperature Sampling
- ๐ก๏ธ Temperature Scaling
- ๐ฐ๏ธ Temporal Data
- โฑ๏ธ Temporal-Difference Learning
- ๐ง Tensor
- ๐งฎ Tensor Parallelism
- โ๏ธ Tensor Processing Unit (TPU)
- ๐ง TensorFlow
- ๐ฑ TensorFlow Lite
- ๐ TensorFlow Serving
- ๐ TensorRT
- โก TensorRT-LLM
- ๐งช Testing
- ๐งญ Text Embedding
- ๐ Text Mining
- ๐ Text Summarization
- ๐๏ธ Text-to-Image
- ๐ฃ๏ธ Text-to-Speech
- ๐ The Pile
- ๐ฏ Thinning
- ๐ต๏ธ Threat Modeling
- ๐๏ธ Threshold
- ๐๏ธ Threshold Tuning
- โก Throughput
- ๐ซ Ticket Status
- โณ Time Delay
- ๐ฐ๏ธ Time Travel
- ๐ฐ๏ธ Time Travelling
- โฐ Timeliness
- ๐ค Together AI
- ๐งน Toil
- ๐ค Token
- โ๏ธ Tokenization
- ๐ค Tokenizer
- ๐งฐ ToolBench
- ๐ฏ Top-k Accuracy
- ๐ฏ Top-k Sampling
- ๐งช TorchServe
- ๐งต Traceability
- ๐งต Tracing
- โก๏ธ Traffic Shifting
- ๐ Traffic Splitting
- โ๏ธ Train-Test Split
- ๐งช Train-Validation-Test Split
- ๐ฏ Training
- ๐ Training Data
- ๐ Training Dynamics
- ๐ฏ Training Error
- ๐งช Training Set
- ๐ง Transactionally Consistent Data Lake
- ๐ Transfer Learning
- ๐งฉ Transformer Decoder-Only
- ๐ Transformer Encoder-Decoder
- ๐ค Transformer Model
- ๐ค Transformers Library
- ๐ Transpose
- ๐ณ Tree-of-Thought
- ๐บ Triplet Loss
- ๐งฉ Triton Inference Server
- ๐ง Trust Region Policy Optimization
- โ Trustworthy AI
- โ TruthfulQA
- ๐ Tumbling Window
- ๐ Tweedie Loss
- ๐งฉ U-Net
- ๐งญ UMAP
- ๐ UUID
- ๐ฏ Uncertainty
- ๐ซ๏ธ Uncertainty Estimation
- ๐ Underfitting
- โ๏ธ Undersampling
- ๐งช Unit Testing
- โ Unit Tests
- ๐๏ธ Unity Catalog
- ๐ค Universal Sentence Encoder
- ๐งฉ Unlabeled Data
- ๐งฝ Unlearning
- ๐งญ Unsupervised Learning
- ๐ Uplift Modeling
- ๐บ Upsampling
- ๐ VC Dimension
- ๐งฑ VGG
- ๐ง VLLM Serving
- ๐ฎ VRAM
- โ Validation
- ๐ Validation Curve
- ๐งช Validation Data
- ๐งช Validation Set
- ๐น Value Function
- ๐ฏ Value Learning
- ๐ Value Network
- ๐ Vanishing Gradient
- ๐ Vanishing Gradient Problem
- ๐๏ธ Variational Autoencoder
- ๐งฎ Variational Inference
- ๐ Vault
- ๐งฒ Vector Database
- ๐งญ Vector Index
- ๐งฉ Vector Quantization
- ๐งญ Vector Search
- โ๏ธ Verification
- ๐๏ธ Version Control
- ๐ข Versioning
- ๐งฉ Vertex AI
- ๐ฌ Video Generation
- ๐๏ธ Video Prediction
- ๐ผ๏ธ Vision-Language Model
- ๐ผ๏ธ Visual Question Answering
- ๐งโ๐ป Visual Studio Code
- ๐ฃ๏ธ Voice Cloning
- ๐ค Voice Recognition
- ๐ฅ Warm Start
- ๐ Warmup
- ๐ง Watermark
- ๐ง Watermarking
- ๐ Wav2Vec 2.0
- ๐ WaveRNN
- ๐ช Weak Supervision
- ๐๏ธ Weaviate
- ๐ WebArena
- ๐๏ธ Weight Initialization
- ๐ข Weight Quantization
- โ๏ธ Weighted Loss
- โ๏ธ Weighting
- ๐งช Weights & Biases
- ๐๏ธ Whisper
- ๐ฃ๏ธ Whisper Large V3
- ๐ Windowed Aggregation
- ๐ช Windowing
- ๐ฃ๏ธ Word Error Rate
- ๐ง Word2Vec
- ๐งฉ WordPiece
- ๐ Workflow
- ๐บ๏ธ Workflow Orchestration
- ๐ World Labs
- ๐ World Model
- ๐ณ XGBoost
- ๐ XLA
- โ๏ธ XLNet
- โ๏ธ Xavier Initialization
- ๐ฏ YOLO
- ๐ง ZeRO
- ๐ Zero Downtime Deployment
- ๐งญ Zero-shot Learning
- ๐ฏ Zero-shot Prompting
- ๐ Zipkin
- ๐งฉ cuDNN
- ๐ฏ g-Formula
- โก gRPC
- ๐ lakeFS
- ๐ mAP
- ๐ผ๏ธ scikit-image
- ๐ scikit-learn
- ๐ฃ๏ธ spaCy
- ๐ t-SNE
- ๐ vLLM