Neural Architecture Search for Neural Decision Trees

Simple item page
dc.contributor.advisorШвай, Надіяuk_UA
dc.contributor.authorМикитишин, Артемuk_UA
dc.date.accessioned2025-09-05T11:33:46Z
dc.date.available2025-09-05T11:33:46Z
dc.date.issued2025
dc.description.abstractNeural Decision Trees (NDTs) have recently gained attention as hybrid models combining the interpretability and structured decision-making of classical decision trees with the representational power of neural networks. Despite promising initial results in specialized applications, certain assumptions underpinning their architecture remain largely unverified. Specifically, Roy and Todorovic (2016) hypothesized that deeper nodes within NDTs would exhibit simpler architectures, requiring fewer convolutional and fully connected layers. To empirically investigate this claim, this thesis employs Neural Architecture Search (NAS) as an unbiased and automated method to explore node complexity across different tree depths, using the CIFAR-10 dataset as a benchmark. Our comprehensive experimental evaluation finds no empirical evidence to support the hypothesis that node complexity systematically decreases with increasing tree depth. These results suggest that assumptions derived from specific applications, such as monocular depth estimation, may not generalize to other domains, underscoring the importance of empirical validation and careful search-space design in neural decision tree research.en_US
dc.identifier.urihttps://ekmair.ukma.edu.ua/handle/123456789/36471
dc.language.isoen_USen_US
dc.statusfirst publisheden_US
dc.subjectNeural Architecture Search (NAS)en_US
dc.subjectNeural Decision Trees (NDTs)en_US
dc.subjectAutomated Machine Learning (Auto ML)en_US
dc.subjectNode Complexityen_US
dc.subjectbachelor`s thesisen_US
dc.titleNeural Architecture Search for Neural Decision Treesen_US
dc.typeOtheren_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
Mykytyshyn_Bakalavrska_robota_1.pdf
Size:
277.3 KB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
Mykytyshyn_Bakalavrska_robota.pdf
Size:
527.24 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
F3 Комп'ютерні науки