Results for "step optimization"

Automatically learning useful internal features (latent variables) that capture salient structure for downstream tasks.

Average of squared residuals; common regression objective.

A gradient method using random minibatches for efficient training on large datasets.

One complete traversal of the training dataset during training.

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

Gradients grow too large, causing divergence; mitigated by clipping, normalization, careful init.

Nonlinear functions enabling networks to approximate complex mappings; ReLU variants dominate modern DL.

Constraining outputs to retrieved or provided sources, often with citation, to improve factual reliability.

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

Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.

A preference-based training method optimizing policies directly from pairwise comparisons without explicit RL loops.

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

Ensuring model behavior matches human goals, norms, and constraints, including reducing harmful or deceptive outputs.

Ordering training samples from easier to harder to improve convergence or generalization.

Training across many devices/silos without centralizing raw data; aggregates updates, not data.

Converts logits to probabilities by exponentiation and normalization; common in classification and LMs.

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

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

Removing weights or neurons to shrink models and improve efficiency; can be structured or unstructured.

Maliciously inserting or altering training data to implant backdoors or degrade performance.

Reconstructing a model or its capabilities via API queries or leaked artifacts.

AI focused on interpreting images/video: classification, detection, segmentation, tracking, and 3D understanding.

Assigning labels per pixel (semantic) or per instance (instance segmentation) to map object boundaries.

Measures how much information an observable random variable carries about unknown parameters.

Estimating parameters by maximizing likelihood of observed data.

A narrow minimum often associated with poorer generalization.

A wide basin often correlated with better generalization.

Gradually increasing learning rate at training start to avoid divergence.

Attention mechanisms that reduce quadratic complexity.

Recovering training data from gradients.