Difficulty: Intermediate

412 terms

Linear Quadratic Regulator Intermediate

Optimal control for linear systems with quadratic cost.

Local Minimum Intermediate

Minimum relative to nearby points.

Log Loss Intermediate

Penalizes confident wrong predictions heavily; standard for classification and language modeling.

Logits Intermediate

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

LoRA Intermediate

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

Loss Function Intermediate

A function measuring prediction error (and sometimes calibration), guiding gradient-based optimization.

Loss Landscape Intermediate

The shape of the loss function over parameter space.

LSTM Intermediate

An RNN variant using gates to mitigate vanishing gradients and capture longer context.

Lyapunov Stability Intermediate

Stability proven via monotonic decrease of Lyapunov function.

Machine Learning Intermediate

A subfield of AI where models learn patterns from data to make predictions or decisions, improving with experience rather than explicit rule-coding.

MAP Estimation Intermediate

Bayesian parameter estimation using the mode of the posterior distribution.

Market Microstructure Intermediate

Mechanics of price formation.

Markov Decision Process Intermediate

Formal framework for sequential decision-making under uncertainty.

Masked Language Model Intermediate

Predicts masked tokens in a sequence, enabling bidirectional context; often used for embeddings rather than generation.

Maximum Likelihood Estimation Intermediate

Estimating parameters by maximizing likelihood of observed data.

Mean Squared Error Intermediate

Average of squared residuals; common regression objective.

Medical Imaging AI Intermediate

AI applied to X-rays, CT, MRI, ultrasound, pathology slides.

Memory Intermediate

Mechanisms for retaining context across turns/sessions: scratchpads, vector memories, structured stores.

Memory Augmentation Intermediate

Extending agents with long-term memory stores.

Message Passing Neural Network Intermediate

GNN framework where nodes iteratively exchange and aggregate messages from neighbors.

Meta-Learning Intermediate

Methods that learn training procedures or initializations so models can adapt quickly to new tasks with little data.

Mixture of Experts Intermediate

Routes inputs to subsets of parameters for scalable capacity.

MLOps Intermediate

Practices for operationalizing ML: versioning, CI/CD, monitoring, retraining, and reliable production management.

Model Intermediate

A parameterized mapping from inputs to outputs; includes architecture + learned parameters.

Model Card Intermediate

Standardized documentation describing intended use, performance, limitations, data, and ethical considerations.

Model Disclosure Intermediate

Requirement to reveal AI usage in legal decisions.

Model Documentation Intermediate

Required descriptions of model behavior and limits.

Model Governance Intermediate

Policies and practices for approving, monitoring, auditing, and documenting models in production.

Model Inventory Intermediate

Central catalog of deployed and experimental models.

Model Inversion Intermediate

Inferring sensitive features of training data.