| Naslov: | Transferring black-box decision making to a white-box model |
|---|
| Avtorji: | ID Žlahtič, Bojan (Avtor)
ID Završnik, Jernej (Avtor)
ID Blažun Vošner, Helena (Avtor)
ID Kokol, Peter (Avtor) |
|---|
| Datoteke: |  electronics-13-01895.pdf (12,25 MB)
MD5: D497C4F8DA07EB2DD861681D62816259
 https://www.mdpi.com/2079-9292/13/10/1895
|
|---|
| Jezik: | Angleški jezik |
|---|
| Vrsta gradiva: | Članek v reviji |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: | FERI - Fakulteta za elektrotehniko, računalništvo in informatiko
FNM - Fakulteta za naravoslovje in matematiko
|
|---|
| Opis: | In the rapidly evolving realm of artificial intelligence (AI), black-box algorithms have exhibited outstanding performance. However, their opaque nature poses challenges in fields like medicine, where the clarity of the decision-making processes is crucial for ensuring trust. Addressing this need, the study aimed to augment these algorithms with explainable AI (XAI) features to enhance transparency. A novel approach was employed, contrasting the decision-making patterns of black-box and white-box models. Where discrepancies were noted, training data were refined to align a white-box model’s decisions closer to its black-box counterpart. Testing this methodology on three distinct medical datasets revealed consistent correlations between the adapted white-box models and their black-box analogs. Notably, integrating this strategy with established methods like local interpretable model-agnostic explanations (LIMEs) and SHapley Additive exPlanations (SHAPs) further enhanced transparency, underscoring the potential value of decision trees as a favored white-box algorithm in medicine due to its inherent explanatory capabilities. The findings highlight a promising path for the integration of the performance of black-box algorithms with the necessity for transparency in critical decision-making domains. |
|---|
| Ključne besede: | explainable artificial intelligence, XAI, machine learning, deep learning, white box, black box |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Poslano v recenzijo: | 05.04.2024 |
|---|
| Datum sprejetja članka: | 10.05.2024 |
|---|
| Datum objave: | 12.05.2024 |
|---|
| Založnik: | MDPI |
|---|
| Leto izida: | 2024 |
|---|
| Št. strani: | 16 str. |
|---|
| Številčenje: | Vol. 13, iss. 10, [article no.] 1895 |
|---|
| PID: | 20.500.12556/DKUM-96749  |
|---|
| UDK: | 004.5 |
|---|
| COBISS.SI-ID: | 195146755 |
|---|
| DOI: | 10.3390/electronics13101895 |
|---|
| ISSN pri članku: | 2079-9292 |
|---|
| Avtorske pravice: | © 2024 by the authors |
|---|
| Datum objave v DKUM: | 27.01.2026 |
|---|
| Število ogledov: | 301 |
|---|
| Število prenosov: | 3 |
|---|
| Metapodatki: |    |
|---|
| Področja: | Ostalo
|
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Skupna ocena: | (0 glasov) |
|---|
| Vaša ocena: | Ocenjevanje je dovoljeno samo prijavljenim uporabnikom. |
|---|
| Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
