Results for "depth estimation"
Tradeoffs between many layers vs many neurons per layer.
Recovering 3D structure from images.
Bayesian parameter estimation using the mode of the posterior distribution.
Inferring the agent’s internal state from noisy sensor data.
Allows gradients to bypass layers, enabling very deep networks.
Early architecture using learned gates for skip connections.
Estimating parameters by maximizing likelihood of observed data.
Monte Carlo method for state estimation.
Probability of data given parameters.
Approximating expectations via random sampling.
Learning physical parameters from data.
Popular optimizer combining momentum and per-parameter adaptive step sizes via first/second moment estimates.
Generates sequences one token at a time, conditioning on past tokens.
Measures how much information an observable random variable carries about unknown parameters.
Systematic error introduced by simplifying assumptions in a learning algorithm.
Combines value estimation (critic) with policy learning (actor).
Exact likelihood generative models using invertible transforms.
Pixel motion estimation between frames.
Simultaneous Localization and Mapping for robotics.
Directed acyclic graph encoding causal relationships.
Optimal estimator for linear dynamic systems.
Formal model linking causal mechanisms and variables.
Probability of treatment assignment given covariates.
Sum of independent variables converges to normal distribution.
Methods like Adam adjusting learning rates dynamically.
Train/test environment mismatch.
Inferring reward function from observed behavior.
Estimating robot position within a map.
Understanding objects exist when unseen.
Risk of incorrect financial models.