Results for "input change"

Identifying abrupt changes in data generation.

Governance of model changes.

The relationship between inputs and outputs changes over time, requiring monitoring and model updates.

Equations governing how system states change over time.

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

Shift in feature distribution over time.

Observing model inputs/outputs, latency, cost, and quality over time to catch regressions and drift.

Matrix of first-order derivatives for vector-valued functions.

Direction of steepest ascent of a function.

Train/test environment mismatch.

Chooses which experts process each token.

Controls the size of parameter updates; too high diverges, too low trains slowly or gets stuck.

Error due to sensitivity to fluctuations in the training dataset.

Exact likelihood generative models using invertible transforms.

Measures joint variability between variables.

Classical controller balancing responsiveness and stability.

Designing input features to expose useful structure (e.g., ratios, lags, aggregations), often crucial outside deep learning.

A single attention mechanism within multi-head attention.

Differences between training and deployed patient populations.

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

Activation max(0, x); improves gradient flow and training speed in deep nets.

Mechanism that computes context-aware mixtures of representations; scales well and captures long-range dependencies.

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

Inputs crafted to cause model errors or unsafe behavior, often imperceptible in vision or subtle in text.

Attacks that manipulate model instructions (especially via retrieved content) to override system goals or exfiltrate data.

Model that compresses input into latent space and reconstructs it.

Sensitivity of a function to input perturbations.

Small prompt changes cause large output changes.

Fast approximation of costly simulations.

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