公开(公告)号：US20190050727A1

公开(公告)日：2019-02-14

申请号：US15869987

申请日：2018-01-12

申请人： Timothy Anderson ,  Monica Martinez-Canales ,  Vinod Sharma

发明人： Timothy Anderson ,  Monica Martinez-Canales ,  Vinod Sharma

IPC分类号： G06N3/08

摘要： Systems and techniques for neural network training are described herein. A training set may be received for a neural network. Here, the neural network may comprise a set of nodes arranged in layers and a set of inter-node weights between nodes in the set of nodes. The neural network may then be iteratively trained to create a trained neural network. An iteration of the training may include generating a random unit vector, creating an update vector by calculating a magnitude for the random unit vector based on a degree that the random unit vector matches a gradient—where the gradient represented by a dual number, and updating a parameter vector for an inter-node weight by subtracting the update vector from a previous parameter vector of the inter-node weight. The trained neural network may then be used to classify data.

公开(公告)号：US20190050692A1

公开(公告)日：2019-02-14

申请号：US15855763

申请日：2017-12-27

申请人： Vinod Sharma ,  Monica Martinez-Canales ,  Peggy Jo Irelan ,  Malini Krishnan Bhandaru ,  Rita Chattopadhyay ,  Soila Pertet Kavulya

发明人： Vinod Sharma ,  Monica Martinez-Canales ,  Peggy Jo Irelan ,  Malini Krishnan Bhandaru ,  Rita Chattopadhyay ,  Soila Pertet Kavulya

IPC分类号： G06K9/62 ,  G06K9/00 ,  G06K9/66 ,  G06K9/20

CPC分类号： G06K9/6292 ,  G06K9/00805 ,  G06K9/00825 ,  G06K9/00845 ,  G06K9/209 ,  G06K9/66

摘要： Various systems and methods for implementing context-based digital signal processing are described herein. An object detection system includes a processor to: access sensor data from a first sensor and a second sensor integrated in a vehicle; access an operating context of the vehicle; assign a first weight to a first object detection result from sensor data of the first sensor, the first weight adjusted based on the operating context; assign a second weight to a second object detection result from sensor data of the second sensor, the second weight adjusted based on the operating context; and perform a combined object detection technique by combining the first object detection result weighted by the first weight and the second object detection result weighted by the second weight.