Results for "data → model"

154 results

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.

Machine Learning
Supervised Learning Intermediate

Learning a function from input-output pairs (labeled data), optimizing performance on predicting outputs for unseen inputs.

Machine Learning
Self-Supervised Learning Intermediate

Learning from data by constructing “pseudo-labels” (e.g., next-token prediction, masked modeling) without manual annotation.

Machine Learning
Meta-Learning Intermediate

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

Machine Learning
Objective Function Intermediate

A scalar measure optimized during training, typically expected loss over data, sometimes with regularization terms.

Optimization
Bias–Variance Tradeoff Intermediate

A conceptual framework describing error as the sum of systematic error (bias) and sensitivity to data (variance).

Foundations & Theory
Train/Validation/Test Split Intermediate

Separating data into training (fit), validation (tune), and test (final estimate) to avoid leakage and optimism bias.

Evaluation & Benchmarking
Tool Use Intermediate

Letting an LLM call external functions/APIs to fetch data, compute, or take actions, improving reliability.

Agents & Autonomy
Differential Privacy Intermediate

A formal privacy framework ensuring outputs do not reveal much about any single individual’s data contribution.

Security & Privacy
CI/CD for ML Intermediate

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

MLOps & Infrastructure
Experiment Tracking Intermediate

Logging hyperparameters, code versions, data snapshots, and results to reproduce and compare experiments.

Evaluation & Benchmarking
Reproducibility Intermediate

Ability to replicate results given same code/data; harder in distributed training and nondeterministic ops.

Foundations & Theory
Privacy Attack Intermediate

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

Foundations & Theory
Maximum Likelihood Estimation Intermediate

Estimating parameters by maximizing likelihood of observed data.

AI Economics & Strategy
Off-Policy Learning Intermediate

Learning from data generated by a different policy.

AI Economics & Strategy
On-Policy Learning Intermediate

Learning only from current policy’s data.

AI Economics & Strategy
Gradient Leakage Intermediate

Recovering training data from gradients.

AI Economics & Strategy
Graph Neural Network Intermediate

Neural networks that operate on graph-structured data by propagating information along edges.

Model Architectures
Time Series Intermediate

Sequential data indexed by time.

Time Series
Change Point Detection Intermediate

Identifying abrupt changes in data generation.

Time Series
Simpson’s Paradox Advanced

Trend reversal when data is aggregated improperly.

Causal AI & Interpretability
Chinchilla Scaling Intermediate

Scaling law optimizing compute vs data.

AI Economics & Strategy
Likelihood Function Advanced

Probability of data given parameters.

Probability & Statistics
Posterior Distribution Advanced

Updated belief after observing data.

Probability & Statistics
Prior Distribution Advanced

Belief before observing data.

Probability & Statistics
Perception Stack Advanced

Software pipeline converting raw sensor data into structured representations.

Robotics & Embodied AI
State Estimation Advanced

Inferring the agent’s internal state from noisy sensor data.

Robotics & Embodied AI
System Identification Advanced

Learning physical parameters from data.

Simulation & Sim-to-Real
Synthetic Sensors Advanced

Artificial sensor data generated in simulation.

Simulation & Sim-to-Real
Hybrid Training Advanced

Combining simulation and real-world data.

Simulation & Sim-to-Real