Results for "probability over text"
Enables external computation or lookup.
Ensuring models comply with lending fairness laws.
A formal privacy framework ensuring outputs do not reveal much about any single individual’s data contribution.
Measures a model’s ability to fit random noise; used to bound generalization error.
Methods that learn training procedures or initializations so models can adapt quickly to new tasks with little data.
A scalar measure optimized during training, typically expected loss over data, sometimes with regularization terms.
Designing input features to expose useful structure (e.g., ratios, lags, aggregations), often crucial outside deep learning.
How well a model performs on new data drawn from the same (or similar) distribution as training.
Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.
Maximum number of tokens the model can attend to in one forward pass; constrains long-document reasoning.
An RNN variant using gates to mitigate vanishing gradients and capture longer context.
A datastore optimized for similarity search over embeddings, enabling semantic retrieval at scale.
When some classes are rare, requiring reweighting, resampling, or specialized metrics.
Protecting data during network transfer and while stored; essential for ML pipelines handling sensitive data.
Processes and controls for data quality, access, lineage, retention, and compliance across the AI lifecycle.
Tendency to trust automated suggestions even when incorrect; mitigated by UI design, training, and checks.
Mechanisms for retaining context across turns/sessions: scratchpads, vector memories, structured stores.
Gradually increasing learning rate at training start to avoid divergence.
Expected cumulative reward from a state or state-action pair.
Balancing learning new behaviors vs exploiting known rewards.
Separates planning from execution in agent architectures.
Extending agents with long-term memory stores.
Models evaluating and improving their own outputs.
Probabilistic energy-based neural network with hidden variables.
Probabilistic graphical model for structured prediction.
Diffusion model trained to remove noise step by step.
Pixel-level separation of individual object instances.
Pixel-wise classification of image regions.
Pixel motion estimation between frames.
Models time evolution via hidden states.