Results for "physical modeling"

Human-like understanding of physical behavior.

Software simulating physical laws.

Physical form contributes to computation.

Hardware components that execute physical actions.

High-fidelity virtual model of a physical system.

Ensuring robots do not harm humans.

Intelligence emerges from interaction with the physical world.

AI systems that perceive and act in the physical world through sensors and actuators.

Devices measuring physical quantities (vision, lidar, force, IMU, etc.).

Learning physical parameters from data.

The physical system being controlled.

Motion considering forces and mass.

Artificial sensor data generated in simulation.

Modeling interactions with environment.

Modeling environment evolution in latent space.

Modeling chemical systems computationally.

Field combining mechanics, control, perception, and AI to build autonomous machines.

Internal sensing of joint positions, velocities, and forces.

Motion of solid objects under forces.

Systems where failure causes physical harm.

Penalizes confident wrong predictions heavily; standard for classification and language modeling.

Networks with recurrent connections for sequences; largely supplanted by Transformers for many tasks.

Converting text into discrete units (tokens) for modeling; subword tokenizers balance vocabulary size and coverage.

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

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

Models time evolution via hidden states.

CNNs applied to time series.

Differences between simulated and real physics.

Learning from data by constructing “pseudo-labels” (e.g., next-token prediction, masked modeling) without manual annotation.

Learning structure from unlabeled data, such as discovering groups, compressing representations, or modeling data distributions.