Invention Grant
- Patent Title: Neural trees
-
Application No.: US16043131Application Date: 2018-07-23
-
Publication No.: US11676078B2Publication Date: 2023-06-13
- Inventor: Aditya Vithal Nori , Antonio Criminisi , Ryutaro Tanno
- Applicant: Microsoft Technology Licensing, LLC
- Applicant Address: US WA Redmond
- Assignee: Microsoft Technology Licensing, LLC
- Current Assignee: Microsoft Technology Licensing, LLC
- Current Assignee Address: US WA Redmond
- Agency: Barta, Jones & Foley, PLLC
- Priority: GB 10736 2018.06.29
- Main IPC: G06N20/00
- IPC: G06N20/00 ; G06N20/20 ; G06N3/082 ; G06F17/18 ; G06N3/04 ; G06F18/243 ; G06V10/764 ; G06V10/82 ; G06V10/44

Abstract:
A predictor has a memory which stores at least one example for which an associated outcome is not known. The memory stores at least one decision tree comprising a plurality of nodes connected by edges, the nodes comprising a root node, internal nodes and leaf nodes. Individual ones of the nodes and individual ones of the edges each have an assigned module, comprising parameterized, differentiable operations, such that for each of the internal nodes the module computes a binary outcome for selecting a child node of the internal node. The predictor has a processor configured to compute the prediction by processing the example using a plurality of the differentiable operations selected according to a path through the tree from the root node to a leaf node.
Public/Granted literature
- US20200005148A1 NEURAL TREES Public/Granted day:2020-01-02
Information query