Method and system for invariant pattern recognition

摘要

An adaptive pattern recognition system optimizes an invariance objective and an input fidelity objective to accurately recognize input patterns in the presence of arbitrary input transformations. A fixed state or value of a feature output can nonlinearly reconstruct or generate multiple spatially distant input patterns and respond similarly to multiple spatially distant input patterns, while preserving the ability to efficiently evaluate the input fidelity objective. Exemplary networks, including a novel factorization of a third-order Boltzmann machine, exhibit multilayered, unsupervised learning of arbitrary transformations, and learn rich, complex features even in the absence of labeled data. These features are then used to classify unknown input patterns, to perform dimensionality reduction or compression.

主权项

1. A method to facilitate pattern recognition comprising:
processing a set of vectors into feature vectors; wherein the processing comprises employing machine learning component adjusted parameters; wherein the machine learning component adjusted parameters are adjusted based at least in part on at least partially conflicting learning objectives including an input fidelity objective and an invariance objective, and are further adjusted at least in part by adding one or more scaled derivatives of the input fidelity objective approximately concurrently with one or more scaled derivatives of the invariance objective to one or more of the machine learning component adjusted parameters.