In a hierarchical neural network having a module structure, learning necessary for detection
of a new feature class is executed by a processing module which has not finished learning …

Tuning a neural network may include selecting a portion of a first neural network for
modification to increase computational efficiency and generating, using a processor, a …

A method of managing memory usage of a stored training set for classification includes
calculating one or both of a first similarity metric and a second similarity metric. The first …

An image-based pattern recognizer and a method and appa ratus for making Such a pattern
recognizer are disclosed. By employing positional coding, the meaning of any feature …

Deep machine learning methods and apparatus related to manipulation of an object by an
end effector of a robot. Some implementations relate to training a deep neural network to …

US PATENT DOCUMENTS baRank. The training data is first processed and organized by a
host computing device, and then streamed to the FPGA for direct access by the FPGA to …

A system and method for selecting a training data set from a set of multidimensional
geophysical input data samples for training a model to predict target data. The input data …

Executing a neural network includes generating an output tile of a first layer of the neural
network by processing an input tile to the first layer and storing the output tile of the first layer …

Identifying objects in images is a difficult problem, particu larly in cases an original image is
noisy or has areas narrow in color or grayscale gradient. A technique employing a …

Deep machine learning methods and apparatus related to manipulation of an object by an
end effector of a robot. Some implementations relate to training a semantic grasping model …