A Novel Methodology for Measuring the Abstraction Capabilities of Image Recognition Algorithms
Creating a widely excepted model on the measure of intelligence became inevitable due to the existence of an abundance of different intelligent systems. Measuring intelligence would provide feedback for the developers and ultimately lead us to create better artificial systems. In the present paper,...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/7/8/152 |
| _version_ | 1797523372424298496 |
|---|---|
| author | Márton Gyula Hudáky Péter Lehotay-Kéry Attila Kiss |
| author_facet | Márton Gyula Hudáky Péter Lehotay-Kéry Attila Kiss |
| author_sort | Márton Gyula Hudáky |
| collection | DOAJ |
| description | Creating a widely excepted model on the measure of intelligence became inevitable due to the existence of an abundance of different intelligent systems. Measuring intelligence would provide feedback for the developers and ultimately lead us to create better artificial systems. In the present paper, we show a solution where learning as a process is examined, aiming to detect pre-written solutions and separate them from the knowledge acquired by the system. In our approach, we examine image recognition software by executing different transformations on objects and detect if the software was resilient to it. A system with the required intelligence is supposed to become resilient to the transformation after experiencing it several times. The method is successfully tested on a simple neural network, which is not able to learn most of the transformations examined. The method can be applied to any image recognition software to test its abstraction capabilities. |
| first_indexed | 2024-03-10T08:42:02Z |
| format | Article |
| id | doaj.art-78022b62d0544e91af527b00691e5f27 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T08:42:02Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-78022b62d0544e91af527b00691e5f272023-11-22T08:14:09ZengMDPI AGJournal of Imaging2313-433X2021-08-017815210.3390/jimaging7080152A Novel Methodology for Measuring the Abstraction Capabilities of Image Recognition AlgorithmsMárton Gyula Hudáky0Péter Lehotay-Kéry1Attila Kiss2Department of Information Systems, ELTE Eötvös Loránd University, 1117 Budapest, HungaryDepartment of Information Systems, ELTE Eötvös Loránd University, 1117 Budapest, HungaryDepartment of Information Systems, ELTE Eötvös Loránd University, 1117 Budapest, HungaryCreating a widely excepted model on the measure of intelligence became inevitable due to the existence of an abundance of different intelligent systems. Measuring intelligence would provide feedback for the developers and ultimately lead us to create better artificial systems. In the present paper, we show a solution where learning as a process is examined, aiming to detect pre-written solutions and separate them from the knowledge acquired by the system. In our approach, we examine image recognition software by executing different transformations on objects and detect if the software was resilient to it. A system with the required intelligence is supposed to become resilient to the transformation after experiencing it several times. The method is successfully tested on a simple neural network, which is not able to learn most of the transformations examined. The method can be applied to any image recognition software to test its abstraction capabilities.https://www.mdpi.com/2313-433X/7/8/152artificial intelligenceneural networksabstractionimage recognition |
| spellingShingle | Márton Gyula Hudáky Péter Lehotay-Kéry Attila Kiss A Novel Methodology for Measuring the Abstraction Capabilities of Image Recognition Algorithms Journal of Imaging artificial intelligence neural networks abstraction image recognition |
| title | A Novel Methodology for Measuring the Abstraction Capabilities of Image Recognition Algorithms |
| title_full | A Novel Methodology for Measuring the Abstraction Capabilities of Image Recognition Algorithms |
| title_fullStr | A Novel Methodology for Measuring the Abstraction Capabilities of Image Recognition Algorithms |
| title_full_unstemmed | A Novel Methodology for Measuring the Abstraction Capabilities of Image Recognition Algorithms |
| title_short | A Novel Methodology for Measuring the Abstraction Capabilities of Image Recognition Algorithms |
| title_sort | novel methodology for measuring the abstraction capabilities of image recognition algorithms |
| topic | artificial intelligence neural networks abstraction image recognition |
| url | https://www.mdpi.com/2313-433X/7/8/152 |
| work_keys_str_mv | AT martongyulahudaky anovelmethodologyformeasuringtheabstractioncapabilitiesofimagerecognitionalgorithms AT peterlehotaykery anovelmethodologyformeasuringtheabstractioncapabilitiesofimagerecognitionalgorithms AT attilakiss anovelmethodologyformeasuringtheabstractioncapabilitiesofimagerecognitionalgorithms AT martongyulahudaky novelmethodologyformeasuringtheabstractioncapabilitiesofimagerecognitionalgorithms AT peterlehotaykery novelmethodologyformeasuringtheabstractioncapabilitiesofimagerecognitionalgorithms AT attilakiss novelmethodologyformeasuringtheabstractioncapabilitiesofimagerecognitionalgorithms |