Difficulty: Intermediate

412 terms

On-Policy Learning Intermediate

Learning only from current policy’s data.

Online Inference Intermediate

Low-latency prediction per request.

Online Learning Intermediate

Learning where data arrives sequentially and the model updates continuously, often under changing distributions.

Open-Weight Model Intermediate

Models whose weights are publicly available.

Optical Flow Intermediate

Pixel motion estimation between frames.

Optimal Control Intermediate

Finding control policies minimizing cumulative cost.

Orchestration Intermediate

Coordinating tools, models, and steps (retrieval, calls, validation) to deliver reliable end-to-end behavior.

Overconfidence Intermediate

Probabilities do not reflect true correctness.

Overfitting Intermediate

When a model fits noise/idiosyncrasies of training data and performs poorly on unseen data.

Overgeneralization Intermediate

Applying learned patterns incorrectly.

PAC Learning Intermediate

A model is PAC-learnable if it can, with high probability, learn an approximately correct hypothesis from finite samples.

Parameter Sharing Intermediate

Using same parameters across different parts of a model.

Parameter-Efficient Fine-Tuning Intermediate

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

Parameters Intermediate

The learned numeric values of a model adjusted during training to minimize a loss function.

Particle Filter Intermediate

Monte Carlo method for state estimation.

Perplexity Intermediate

Exponential of average negative log-likelihood; lower means better predictive fit, not necessarily better utility.

PID Controller Intermediate

Classical controller balancing responsiveness and stability.

PII Intermediate

Information that can identify an individual (directly or indirectly); requires careful handling and compliance.

Planner-Executor Intermediate

Separates planning from execution in agent architectures.

Planning Intermediate

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

Plant Intermediate

The physical system being controlled.

Policy Intermediate

Strategy mapping states to actions.

Policy Gradient Intermediate

Optimizing policies directly via gradient ascent on expected reward.

Positional Encoding Intermediate

Injects sequence order into Transformers, since attention alone is permutation-invariant.

PR Curve Intermediate

Often more informative than ROC on imbalanced datasets; focuses on positive class performance.

Precision Intermediate

Of predicted positives, the fraction that are truly positive; sensitive to false positives.

Prediction Drift Intermediate

Shift in model outputs.

Predictive Policing Intermediate

AI predicting crime patterns (highly controversial).

Privacy Attack Intermediate

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Prognostic Model Intermediate

Predicting disease progression or survival.