Difficulty: Intermediate

412 terms

3D Reconstruction Intermediate

Recovering 3D structure from images.

A/B Testing Intermediate

Controlled experiment comparing variants by random assignment to estimate causal effects of changes.

Absolute Positional Encoding Intermediate

Encodes token position explicitly, often via sinusoids.

Accuracy Intermediate

Fraction of correct predictions; can be misleading on imbalanced datasets.

Acoustic Model Intermediate

Maps audio signals to linguistic units.

Action Space Intermediate

Set of all actions available to the agent.

Activation Function Intermediate

Nonlinear functions enabling networks to approximate complex mappings; ReLU variants dominate modern DL.

Active Learning Intermediate

Selecting the most informative samples to label (e.g., uncertainty sampling) to reduce labeling cost.

Actor-Critic Intermediate

Combines value estimation (critic) with policy learning (actor).

Adam Intermediate

Popular optimizer combining momentum and per-parameter adaptive step sizes via first/second moment estimates.

Adaptive Optimization Intermediate

Methods like Adam adjusting learning rates dynamically.

Adversarial Example Intermediate

Inputs crafted to cause model errors or unsafe behavior, often imperceptible in vision or subtle in text.

Agent Intermediate

A system that perceives state, selects actions, and pursues goals—often combining LLM reasoning with tools and memory.

Agent Loop Intermediate

Continuous cycle of observation, reasoning, action, and feedback.

AI Adoption Curve Intermediate

Organizational uptake of AI technologies.

AI Center of Excellence Intermediate

Centralized AI expertise group.

AI Hallucination Intermediate

Fabrication of cases or statutes by LLMs.

AI Treaty Intermediate

International agreements on AI.

Algorithmic Accountability Intermediate

Ensuring decisions can be explained and traced.

Algorithmic Bias Intermediate

Unequal performance across demographic groups.

Algorithmic Trading Intermediate

AI-driven buying/selling of financial assets.

Alignment Intermediate

Ensuring model behavior matches human goals, norms, and constraints, including reducing harmful or deceptive outputs.

Alignment Research Intermediate

Research ensuring AI remains safe.

Alpha Intermediate

Returns above benchmark.

ARIMA Intermediate

Classical statistical time-series model.

Artificial Intelligence Intermediate

The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, planning, and decision-making—via algori...

Attention Intermediate

Mechanism that computes context-aware mixtures of representations; scales well and captures long-range dependencies.

Attention Head Intermediate

A single attention mechanism within multi-head attention.

Attorney-Client Privilege Intermediate

Protection of private legal communications.

AUC Intermediate

Scalar summary of ROC; measures ranking ability, not calibration.