Results for "data → model"

High-fidelity virtual model of a physical system.

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

Model trained to predict human preferences (or utility) for candidate outputs; used in RLHF-style pipelines.

Predicts next state given current state and action.

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

A parameterized function composed of interconnected units organized in layers with nonlinear activations.

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

Autoencoder using probabilistic latent variables and KL regularization.

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

Agents communicate via shared state.

Chooses which experts process each token.

Differences between simulated and real physics.

Models effects of interventions (do(X=x)).

Differences between training and deployed patient populations.

RL without explicit dynamics model.

Networks using convolution operations with weight sharing and locality, effective for images and signals.

Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.

A datastore optimized for similarity search over embeddings, enabling semantic retrieval at scale.

Updating beliefs about parameters using observed evidence and prior distributions.

Bayesian parameter estimation using the mode of the posterior distribution.

Techniques to handle longer documents without quadratic cost.

Generator produces limited variety of outputs.

Persistent directional movement over time.

Identifying abrupt changes in data generation.

Mathematical foundation for ML involving vector spaces, matrices, and linear transformations.

Decomposes a matrix into orthogonal components; used in embeddings and compression.

Number of linearly independent rows or columns.

Centralized AI expertise group.

Devices measuring physical quantities (vision, lidar, force, IMU, etc.).

External sensing of surroundings (vision, audio, lidar).