Sentence examples for maps are learned from inspiring English sources

Grid-based maps are learned using artificial neural networks and naive Bayesian integration.

In adaptive systems this inverse mapping is learned from examples.

Local features are pooled in a region and a mapping is learned from feature distributions to semantic action labels [12].

Then from these high-level representations, a feature mapping is learned to create a latent common representation as to bridge the gap between heterogeneous feature spaces.

Then the random mapping and the right-shift mapping were learned.

This mapping was learned prior to scanning and practiced until the participant had responded to 5 consecutive trials correctly.

In the standard PbD formulation of this problem, a parametrised function is learned, mapping from state, x t, which denotes the current position of the demonstrator's hand to x ̇ t, the hand's displacement.

Subsequently, a linear regression function is learned that maps appearance features represented by texton distributions to the roughness estimate.

The parameters defining this mapping (weights and threshold values) are learned during the classifier training by minimizing an error function.

From this, a simultaneous optimization objective is performed where, first, two linear transformations are learned to map the source and target data into a common subspace.

Then, these parameters are learned by sensorimotor maps between visual information (flow) and motor commands.