Difficulty: Intermediate

412 terms

Change Point Detection Intermediate

Identifying abrupt changes in data generation.
Chinchilla Scaling Intermediate

Scaling law optimizing compute vs data.
Chunking Intermediate

Breaking documents into pieces for retrieval; chunk size/overlap strongly affect RAG quality.
CI/CD for ML Intermediate

Automated testing and deployment processes for models and data workflows, extending DevOps to ML artifacts.
Class Imbalance Intermediate

When some classes are rare, requiring reweighting, resampling, or specialized metrics.
Clinical Decision Support Intermediate

AI systems assisting clinicians with diagnosis or treatment decisions.
Clinical Validation Intermediate

Testing AI under actual clinical conditions.
CLIP Intermediate

Joint vision-language model aligning images and text.
Closed Model Intermediate

Models accessible only via service APIs.
Cold Start Intermediate

Startup latency for services.
Commoditization Intermediate

Declining differentiation among models.
Computational Learning Theory Intermediate

A theoretical framework analyzing what classes of functions can be learned, how efficiently, and with what guarantees.
Compute Intermediate

Hardware resources used for training/inference; constrained by memory bandwidth, FLOPs, and parallelism.
Compute Governance Intermediate

Regulating access to large-scale compute.
Compute Scaling Intermediate

Increasing model capacity via compute.
Computer Vision Intermediate

AI focused on interpreting images/video: classification, detection, segmentation, tracking, and 3D understanding.
Computer-Aided Diagnosis Intermediate

Automated assistance identifying disease indicators.
Concept Drift Intermediate

The relationship between inputs and outputs changes over time, requiring monitoring and model updates.
Conditional Random Field Intermediate

Probabilistic graphical model for structured prediction.
Confounding Intermediate

A hidden variable influences both cause and effect, biasing naive estimates of causal impact.
Confusion Matrix Intermediate

A table summarizing classification outcomes, foundational for metrics like precision, recall, specificity.
Constrained Optimization Intermediate

Optimization under equality/inequality constraints.
Context Compression Intermediate

Techniques to handle longer documents without quadratic cost.
Context Window Intermediate

Maximum number of tokens the model can attend to in one forward pass; constrains long-document reasoning.
Control Theory Intermediate

Mathematical framework for controlling dynamic systems.
Controller Intermediate

Algorithm computing control actions.
Convex Optimization Intermediate

Optimization problems where any local minimum is global.
Convolutional Neural Network Intermediate

Networks using convolution operations with weight sharing and locality, effective for images and signals.
Cooperative AI Intermediate

Designing AI to cooperate with humans and each other.
Cost Attribution Intermediate

Assigning AI costs to business units.