US 2019/0156184 A1 · LOCALIZING TREE-BASED CONVOLUTIONAL NEURAL NETWORKS

Abstract

In an approach to localizing tree-based convolutional neural networks, a method includes creating a first tree-based convolution layer (TBCL) corresponding to a tree, where the tree includes a first plurality of nodes and a node that has been indicated to be a first pivotal node. The first TBCL includes a second plurality of nodes and a second pivotal node having a feature vector based on node data from the first pivotal node. The method also includes creating a second TBCL corresponding to the tree. The second TBCL may include a third plurality of nodes. The method further includes determining a feature vector a third pivotal node in the third plurality of nodes based on the feature vectors from: (i) the second pivotal node, (ii) a parent node of the second pivotal node, and (ii) a child node of the second pivotal node.

Claims20

Dependent claims

A method, comprising:

creating, by one or more processors, a first tree-based convolution layer (TBCL) corresponding to a tree, wherein the tree includes a first plurality of nodes, wherein the tree includes a node that has been indicated to be a first pivotal node, wherein the first TBCL includes a second plurality of nodes and wherein the first TBCL includes a second pivotal node having a feature vector based on node data from the first pivotal node;
creating, by one or more processors, a second TBCL corresponding to the tree, wherein the second TBCL includes a third plurality of nodes;
and
determining, by one or more processors, a feature vector of a third pivotal node in the third plurality of nodes based on the feature vectors from:
(i) the second pivotal node, (ii) a parent node of the second pivotal node, and (ii) a child node of the second pivotal node.

2 more elements

A computer program product, comprising:

one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to create a first tree-based convolution layer (TBCL) corresponding to a tree, wherein the tree includes a first plurality of nodes, wherein the tree includes a node that has been indicated to be a first pivotal node, wherein the first TBCL includes a second plurality of nodes and wherein the first TBCL includes a second pivotal node having a feature vector based on node data from the first pivotal node;
program instructions to create a second TBCL corresponding to the tree, wherein the second TBCL includes a third plurality of nodes;
and
program instructions to determine a feature vector for a third pivotal node in the third plurality of nodes determined by the feature vectors from:
(i) the second pivotal node, (ii) a parent node of the second pivotal node, and (ii) a child node of the second pivotal node.

3 more elements

A computer system, comprising:

one or more computer processors;
one or more computer readable storage devices;
program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising:
program instructions to create a first tree-based convolution layer (TBCL) corresponding to a tree, wherein the tree includes a first plurality of nodes, wherein the tree includes a node that has been indicated to be a first pivotal node, wherein the first TBCL includes a second plurality of nodes and wherein the first TBCL includes a second pivotal node having a feature vector based on node data from the first pivotal node;
program instructions to create a second TBCL corresponding to the tree, wherein the second TBCL includes a third plurality of nodes;
and
program instructions to determine a feature vector for a third pivotal node in the third plurality of nodes determined by the feature vectors from:
(i) the second pivotal node, (ii) a parent node of the second pivotal node, and (ii) a child node of the second pivotal node.

5 more elements

Dependencies are inferred from the claim text.

Localizing tree-based convolutional neural networks

Life of this patent

Localizing tree-based convolutional neural networks

Life of this patent

Abstract

Claims20