-
公开(公告)号：US20190005384A1
公开(公告)日：2019-01-03
申请号：US15637837
申请日：2017-06-29
Applicant: General Electric Company
Inventor： Bharath Ram Sundar , Radhika Madhavan , Hariharan Ravishankar
IPC: G06N3/08
Abstract: The present approach relates to the processing of edge information related to graph topology using a neural network. In one aspect, graph topology information along with edge weights are added as a first hidden layer of a neural network. In this manner, better spatial information is transferred to the neural network.
-
公开(公告)号：US11232344B2
公开(公告)日：2022-01-25
申请号：US15799698
申请日：2017-10-31
Applicant: General Electric Company
Inventor： Hariharan Ravishankar , Bharath Ram Sundar , Prasad Sudhakar , Rahul Venkataramani , Vivek Vaidya
Abstract: The present approach relates to feature ranking within deep neural networks in a multi-task and/or multi-label setting. Approaches are described to identify features that are task-specific as well as features that are shared across multiple tasks. In addition to facilitating interpretability, the selected subset of features can be used to make efficient models leading to better stability & regularization along with reduced compute and memory.
-
公开(公告)号：US20190130247A1
公开(公告)日：2019-05-02
申请号：US15799698
申请日：2017-10-31
Applicant: General Electric Company
Inventor： Hariharan Ravishankar , Bharath Ram Sundar , Prasad Sudhakar , Rahul Venkataramani , Vivek Vaidya
Abstract: The present approach relates to feature ranking within deep neural networks in a multi-task and/or multi-label setting. Approaches are described to identify features that are task-specific as well as features that are shared across multiple tasks. In addition to facilitating interpretability, the selected subset of features can be used to make efficient models leading to better stability & regularization along with reduced compute and memory.
-
-
Search Results
3
records
(took 0.014 seconds)
