Results for "neural networks"

Converting audio speech into text, often using encoder-decoder or transducer architectures.

Graphs containing multiple node or edge types with different semantics.

GNN using attention to weight neighbor contributions dynamically.

Pixel-wise classification of image regions.

Transformer applied to image patches.

Predicting future values from past observations.

AI proposing scientific hypotheses.

Methods to set starting weights to preserve signal/gradient scales across layers.

Raw model outputs before converting to probabilities; manipulated during decoding and calibration.

Probabilistic energy-based neural network with hidden variables.

The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, planning, and decision-making—via algori...

Training one model on multiple tasks simultaneously to improve generalization through shared structure.

The internal space where learned representations live; operations here often correlate with semantics or generative factors.

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

Training objective where the model predicts the next token given previous tokens (causal modeling).

Stepwise reasoning patterns that can improve multi-step tasks; often handled implicitly or summarized for safety/privacy.

Automated detection/prevention of disallowed outputs (toxicity, self-harm, illegal instruction, etc.).

Feature attribution method grounded in cooperative game theory for explaining predictions in tabular settings.

Reducing numeric precision of weights/activations to speed inference and reduce memory with acceptable accuracy loss.

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

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

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 divergence between true and predicted probability distributions.

AI subfield dealing with understanding and generating human language, including syntax, semantics, and pragmatics.

A point where gradient is zero but is neither a max nor min; common in deep nets.

Generating speech audio from text, with control over prosody, speaker identity, and style.

Gradually increasing learning rate at training start to avoid divergence.

A narrow hidden layer forcing compact representations.

Extending agents with long-term memory stores.