Structured Differential Learning for Automatic Threshold Setting
We introduce a technique that can automatically tune the parameters of a rule-based computer vision system comprised of thresholds, combinational logic, and time constants. This lets us retain the flexibility and perspicacity of a conventionally structured system while allowing us to perform approxi...
Saved in:
| Main Authors | , |
|---|---|
| Format | Journal Article |
| Language | English |
| Published |
01.08.2018
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | We introduce a technique that can automatically tune the parameters of a
rule-based computer vision system comprised of thresholds, combinational logic,
and time constants. This lets us retain the flexibility and perspicacity of a
conventionally structured system while allowing us to perform approximate
gradient descent using labeled data. While this is only a heuristic procedure,
as far as we are aware there is no other efficient technique for tuning such
systems. We describe the components of the system and the associated supervised
learning mechanism. We also demonstrate the utility of the algorithm by
comparing its performance versus hand tuning for an automotive headlight
controller. Despite having over 100 parameters, the method is able to
profitably adjust the system values given just the desired output for a number
of videos. |
|---|---|
| AbstractList | We introduce a technique that can automatically tune the parameters of a
rule-based computer vision system comprised of thresholds, combinational logic,
and time constants. This lets us retain the flexibility and perspicacity of a
conventionally structured system while allowing us to perform approximate
gradient descent using labeled data. While this is only a heuristic procedure,
as far as we are aware there is no other efficient technique for tuning such
systems. We describe the components of the system and the associated supervised
learning mechanism. We also demonstrate the utility of the algorithm by
comparing its performance versus hand tuning for an automotive headlight
controller. Despite having over 100 parameters, the method is able to
profitably adjust the system values given just the desired output for a number
of videos. |
| Author | Herta, Benjamin Connell, Jonathan |
| Author_xml | – sequence: 1 givenname: Jonathan surname: Connell fullname: Connell, Jonathan – sequence: 2 givenname: Benjamin surname: Herta fullname: Herta, Benjamin |
| BackLink | https://doi.org/10.48550/arXiv.1808.00361$$DView paper in arXiv |
| BookMark | eNotz71OwzAUhmEPMEDhApjwDSQcx_HfRlV-pUgMzR6Z-JhaSh106iC4e6AwfcMrfdJzzk7ynJGxKwF1a5WCG0-f6aMWFmwNILU4Y7fbQstYFsLA71KMSJhL8hPv0FNO-Y3Hmfh6KfPelzTyfkd42M1T4Fss5adfsNPopwNe_u-K9Q_3_eap6l4enzfrrvLaiEppK1twLqKN4B3q0Yaggg5yFEYB6ldQykvnVBTW6UYYBNO4pm0MGpAoV-z67_ZIGN4p7T19Db-U4UiR38V8ROg |
| ContentType | Journal Article |
| Copyright | http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| Copyright_xml | – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| DBID | AKY EPD GOX |
| DOI | 10.48550/arxiv.1808.00361 |
| DatabaseName | arXiv Computer Science arXiv Statistics arXiv.org |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| ExternalDocumentID | 1808_00361 |
| GroupedDBID | AKY EPD GOX |
| ID | FETCH-LOGICAL-a671-56834099fe8f0a9e6c8dd5d6d3c1750e6b055a3995f1896217e07292427e703e3 |
| IEDL.DBID | GOX |
| IngestDate | Mon Jan 08 05:40:31 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a671-56834099fe8f0a9e6c8dd5d6d3c1750e6b055a3995f1896217e07292427e703e3 |
| Notes | IBM Research Report RC25144 |
| OpenAccessLink | https://arxiv.org/abs/1808.00361 |
| ParticipantIDs | arxiv_primary_1808_00361 |
| PublicationCentury | 2000 |
| PublicationDate | 2018-08-01 |
| PublicationDateYYYYMMDD | 2018-08-01 |
| PublicationDate_xml | – month: 08 year: 2018 text: 2018-08-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationYear | 2018 |
| Score | 1.7077888 |
| SecondaryResourceType | preprint |
| Snippet | We introduce a technique that can automatically tune the parameters of a
rule-based computer vision system comprised of thresholds, combinational logic,
and... |
| SourceID | arxiv |
| SourceType | Open Access Repository |
| SubjectTerms | Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Statistics - Machine Learning |
| Title | Structured Differential Learning for Automatic Threshold Setting |
| URI | https://arxiv.org/abs/1808.00361 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV1NS8QwEB3WPXkRF5X1kxy8FtOvNL3t4rougnrYCr2VJDMVQVT2Q_z5TtKKXryVNpe8Et488uYNwGWhkYtgh5FpWelkGiU_aW-msrHxgwis843C9w9q8ZTd1Xk9APHTC2NWXy-fXT6wXV_FOlgdU69vdpLEW7ZuH-vucjJEcfXrf9dxjRle_SGJ-T7s9dWdmHa_YwQDejuAyTJktG5XhGLWzyPhc_Uq-mzTZ8GFo5huN-8hPlVUDO_a3wqJJQVX8iFU85vqehH1gwsio4o4ypVOWTaVLelWmpKU04g5Kkwdk7UkZWWeG99T2sa6VCwKyOd3M1kWxAeQ0iMYsvanMQiud1KSzNmsVDNXokVMnOfdEMOTlccwDtttPrpsisYj0QQkTv7_dAq7zPu687GdwZBRoHPm1o29CAB_A0Xud-o |
| link.rule.ids | 228,230,783,888 |
| linkProvider | Cornell University |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Structured+Differential+Learning+for+Automatic+Threshold+Setting&rft.au=Connell%2C+Jonathan&rft.au=Herta%2C+Benjamin&rft.date=2018-08-01&rft_id=info:doi/10.48550%2Farxiv.1808.00361&rft.externalDocID=1808_00361 |