Results for "transformations"

Expanding training data via transformations (flips, noise, paraphrases) to improve robustness.

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

Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.

Tracking where data came from and how it was transformed; key for debugging and compliance.

Exact likelihood generative models using invertible transforms.

Models accessible only via service APIs.

Set of vectors closed under addition and scalar multiplication.

Computing end-effector position from joint angles.

Interpreting human gestures.