Collecting observations for machine learning
AssigneeMicrosoft Technology Licensing, LLC
InventorsCheng ZHANG, Wenbo GONG, Richard Eric TURNER, Sebastian TSCHIATSCHEK, José Miguel HERNÁNDEZ LOBATO
Life of this patent
Estimating the term…
Loading patent…
AssigneeMicrosoft Technology Licensing, LLC
InventorsCheng ZHANG, Wenbo GONG, Richard Eric TURNER, Sebastian TSCHIATSCHEK, José Miguel HERNÁNDEZ LOBATO
Estimating the term…
A method of training a model comprising a generative network mapping a latent vector to a feature vector, wherein weights in the generative network are modelled as probabilistic distributions. The method comprises: a) obtaining one or more observed data points, each comprising an incomplete observation of the features in the feature vector; b) training the model based on the observed data points to learn values of the weights of the generative network which map the latent vector to the feature vector; c) from amongst a plurality of potential next features to observe, searching for a target feature of the feature vector which maximizes a measure of expected reduction in uncertainty in a distribution of said weights of the generative network given the observed data points so far; and d) outputting a request to collect a target data point comprising at least the target feature.
A computer-implemented method of training a model comprising one or more neural networks including at least a generative network, the generative network having a latent vector as an input vector and a feature vector as an output vector, each element of the feature vector representing a different one of a set of features, wherein weights applied by at least some nodes in the generative network are each modelled as a probabilistic distribution;
Dependencies are inferred from the claim text.