Results for "changing target relationship"

AdvertisementAd space — search-top

71 results

Parameter-Efficient Fine-Tuning Intermediate

Techniques that fine-tune small additional components rather than all weights to reduce compute and storage.

Foundations & Theory
LoRA Intermediate

PEFT method injecting trainable low-rank matrices into layers, enabling efficient fine-tuning.

Foundations & Theory
Quantization Intermediate

Reducing numeric precision of weights/activations to speed inference and reduce memory with acceptable accuracy loss.

Foundations & Theory
Secure Inference Intermediate

Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.

Foundations & Theory
Human-in-the-Loop Intermediate

System design where humans validate or guide model outputs, especially for high-stakes decisions.

Foundations & Theory
Structured Output Intermediate

Forcing predictable formats for downstream systems; reduces parsing errors and supports validation/guardrails.

Foundations & Theory
Planning Intermediate

Methods for breaking goals into steps; can be classical (A*, STRIPS) or LLM-driven with tool calls.

Foundations & Theory
Computer Vision Intermediate

AI focused on interpreting images/video: classification, detection, segmentation, tracking, and 3D understanding.

Computer Vision
Computational Learning Theory Intermediate

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

AI Economics & Strategy
Sharp Minimum Intermediate

A narrow minimum often associated with poorer generalization.

AI Economics & Strategy
Flat Minimum Intermediate

A wide basin often correlated with better generalization.

AI Economics & Strategy
Emergent Abilities Intermediate

Capabilities that appear only beyond certain model sizes.

AI Economics & Strategy
Action Space Intermediate

Set of all actions available to the agent.

AI Economics & Strategy
Energy-Based Model Intermediate

Models that define an energy landscape rather than explicit probabilities.

Model Architectures
Value Function Intermediate

Expected cumulative reward from a state or state-action pair.

AI Economics & Strategy
Acoustic Model Intermediate

Maps audio signals to linguistic units.

Speech & Audio AI
Q-Function Intermediate

Expected return of taking action in a state.

AI Economics & Strategy
Compute Scaling Intermediate

Increasing model capacity via compute.

AI Economics & Strategy
Cross-Attention Intermediate

Attention between different modalities.

Computer Vision
Data Scaling Intermediate

Increasing performance via more data.

AI Economics & Strategy
Training Cost Intermediate

Cost of model training.

AI Economics & Strategy
Covariance Advanced

Measures joint variability between variables.

Probability & Statistics
Dual Problem Intermediate

Alternative formulation providing bounds.

Foundations & Theory
Feedback Loop Collapse Intermediate

Model trained on its own outputs degrades quality.

Model Failure Modes
Spurious Correlation Intermediate

Model relies on irrelevant signals.

Model Failure Modes
Autoscaling Intermediate

Dynamic resource allocation.

AI Economics & Strategy
Edge Inference Intermediate

Running models locally.

AI Economics & Strategy
Embodied AI Advanced

AI systems that perceive and act in the physical world through sensors and actuators.

Robotics & Embodied AI
Robotics Advanced

Field combining mechanics, control, perception, and AI to build autonomous machines.

Robotics & Embodied AI
Actuator Advanced

Hardware components that execute physical actions.

Robotics & Embodied AI

Welcome to AI Glossary

The free, self-building AI dictionary. Help us keep it free—click an ad once in a while!

Search

Type any question or keyword into the search bar at the top.

Browse

Tap a letter in the A–Z bar to browse terms alphabetically, or filter by domain, industry, or difficulty level.

3D WordGraph

Fly around the interactive 3D graph to explore how AI concepts connect. Click any word to read its full definition.