Relevance Score Assignment For Artificial Neural Network


Ontology type: sgo:Patent     


Patent Info

DATE

N/A

AUTHORS

BACH, SEBASTIAN , SAMEK, Wojciech , MÜLLER, Klaus-Robert , BINDER, ALEXANDER , MONTAVON, Grégoire

ABSTRACT

The task of relevance score assignment to a set of items onto which an artificial neural network is applied is obtained by redistributing an initial relevance score derived from the network output, onto the set of items by reversely propagating the initial relevance score through the artificial neural network so as to obtain a relevance score for each item. In particular, this reverse propagation is applicable to a broader set of artificial neural networks and/or at lower computational efforts by performing same in a manner so that for each neuron, preliminarily redistributed relevance scores of a set of downstream neighbor neurons of the respective neuron are distributed on a set of upstream neighbor neurons of the respective neuron according to a distribution function. More... »

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2746", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/3120", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "name": "BACH, SEBASTIAN", 
        "type": "Person"
      }, 
      {
        "name": "SAMEK, Wojciech", 
        "type": "Person"
      }, 
      {
        "name": "M\u00dcLLER, Klaus-Robert", 
        "type": "Person"
      }, 
      {
        "name": "BINDER, ALEXANDER", 
        "type": "Person"
      }, 
      {
        "name": "MONTAVON, Gr\u00e9goire", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/s0304-3800(02)00257-0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025763367"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-10590-1_53", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032233097", 
          "https://doi.org/10.1007/978-3-319-10590-1_53"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "description": "

The task of relevance score assignment to a set of items onto which an artificial neural network is applied is obtained by redistributing an initial relevance score derived from the network output, onto the set of items by reversely propagating the initial relevance score through the artificial neural network so as to obtain a relevance score for each item. In particular, this reverse propagation is applicable to a broader set of artificial neural networks and/or at lower computational efforts by performing same in a manner so that for each neuron, preliminarily redistributed relevance scores of a set of downstream neighbor neurons of the respective neuron are distributed on a set of upstream neighbor neurons of the respective neuron according to a distribution function.

", "id": "sg:patent.WO-2016150472-A1", "keywords": [ "artificial neural network", "task", "assignment", "score", "network", "propagation", "broad set", "computational effort", "neuron", "neighbor", "distribution function" ], "name": "RELEVANCE SCORE ASSIGNMENT FOR ARTIFICIAL NEURAL NETWORK", "recipient": [ { "id": "https://www.grid.ac/institutes/grid.4561.6", "type": "Organization" }, { "id": "https://www.grid.ac/institutes/grid.6734.6", "type": "Organization" } ], "sameAs": [ "https://app.dimensions.ai/details/patent/WO-2016150472-A1" ], "sdDataset": "patents", "sdDatePublished": "2019-03-07T15:30", "sdLicense": "https://scigraph.springernature.com/explorer/license/", "sdPublisher": { "name": "Springer Nature - SN SciGraph project", "type": "Organization" }, "sdSource": "s3://com.uberresearch.data.dev.patents-pipeline/full_run_10/sn-export/5eb3e5a348d7f117b22cc85fb0b02730/0000100128-0000348334/json_export_0782263a.jsonl", "type": "Patent" } ]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/patent.WO-2016150472-A1'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/patent.WO-2016150472-A1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.WO-2016150472-A1'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.WO-2016150472-A1'


 

This table displays all metadata directly associated to this object as RDF triples.

60 TRIPLES      14 PREDICATES      28 URIs      18 LITERALS      2 BLANK NODES

Subject Predicate Object
1 sg:patent.WO-2016150472-A1 schema:about anzsrc-for:2746
2 anzsrc-for:3120
3 schema:author N715dfdfabb7a4007916ee9e2d4afb355
4 schema:citation sg:pub.10.1007/978-3-319-10590-1_53
5 https://doi.org/10.1016/s0304-3800(02)00257-0
6 schema:description <p num="0000">The task of relevance score assignment to a set of items onto which an artificial neural network is applied is obtained by redistributing an initial relevance score derived from the network output, onto the set of items by reversely propagating the initial relevance score through the artificial neural network so as to obtain a relevance score for each item. In particular, this reverse propagation is applicable to a broader set of artificial neural networks and/or at lower computational efforts by performing same in a manner so that for each neuron, preliminarily redistributed relevance scores of a set of downstream neighbor neurons of the respective neuron are distributed on a set of upstream neighbor neurons of the respective neuron according to a distribution function.</p>
7 schema:keywords artificial neural network
8 assignment
9 broad set
10 computational effort
11 distribution function
12 neighbor
13 network
14 neuron
15 propagation
16 score
17 task
18 schema:name RELEVANCE SCORE ASSIGNMENT FOR ARTIFICIAL NEURAL NETWORK
19 schema:recipient https://www.grid.ac/institutes/grid.4561.6
20 https://www.grid.ac/institutes/grid.6734.6
21 schema:sameAs https://app.dimensions.ai/details/patent/WO-2016150472-A1
22 schema:sdDatePublished 2019-03-07T15:30
23 schema:sdLicense https://scigraph.springernature.com/explorer/license/
24 schema:sdPublisher N4c5d187417fc4da5940fd8468db94d06
25 sgo:license sg:explorer/license/
26 sgo:sdDataset patents
27 rdf:type sgo:Patent
28 N0ae14c9457a24795ada359688ae1ee6d schema:name MÜLLER, Klaus-Robert
29 rdf:type schema:Person
30 N2568c5b1a3e14378940bd1e4718c10a1 rdf:first N0ae14c9457a24795ada359688ae1ee6d
31 rdf:rest Na2a2f557b2b5449a8bbbc8ab424b46bd
32 N4c5d187417fc4da5940fd8468db94d06 schema:name Springer Nature - SN SciGraph project
33 rdf:type schema:Organization
34 N513034e267a94618b6c252a6afa6a45d rdf:first N7d90d3857c6b4509813763343a6bad9d
35 rdf:rest N2568c5b1a3e14378940bd1e4718c10a1
36 N715dfdfabb7a4007916ee9e2d4afb355 rdf:first Ncdd33dc232524205931fb1a39232a4d0
37 rdf:rest N513034e267a94618b6c252a6afa6a45d
38 N7d90d3857c6b4509813763343a6bad9d schema:name SAMEK, Wojciech
39 rdf:type schema:Person
40 Na1a355989ff340da8c3c91757db2683e rdf:first Na77a0df4ce5141d4aa8803099cca6dc2
41 rdf:rest rdf:nil
42 Na2a2f557b2b5449a8bbbc8ab424b46bd rdf:first Ndd8a8f25d93045b0a24a8bbf2fd59842
43 rdf:rest Na1a355989ff340da8c3c91757db2683e
44 Na77a0df4ce5141d4aa8803099cca6dc2 schema:name MONTAVON, Grégoire
45 rdf:type schema:Person
46 Ncdd33dc232524205931fb1a39232a4d0 schema:name BACH, SEBASTIAN
47 rdf:type schema:Person
48 Ndd8a8f25d93045b0a24a8bbf2fd59842 schema:name BINDER, ALEXANDER
49 rdf:type schema:Person
50 anzsrc-for:2746 schema:inDefinedTermSet anzsrc-for:
51 rdf:type schema:DefinedTerm
52 anzsrc-for:3120 schema:inDefinedTermSet anzsrc-for:
53 rdf:type schema:DefinedTerm
54 sg:pub.10.1007/978-3-319-10590-1_53 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032233097
55 https://doi.org/10.1007/978-3-319-10590-1_53
56 rdf:type schema:CreativeWork
57 https://doi.org/10.1016/s0304-3800(02)00257-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025763367
58 rdf:type schema:CreativeWork
59 https://www.grid.ac/institutes/grid.4561.6 schema:Organization
60 https://www.grid.ac/institutes/grid.6734.6 schema:Organization
 




Preview window. Press ESC to close (or click here)


...