Physical Rule-Guided Convolutional Neural Network
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913490861555712 |
|---|---|
| author | Gupta, Kishor Datta Kamal, Marufa Rifat, Rakib Hossain Haque, Mohd Ariful George, Roy |
| author_facet | Gupta, Kishor Datta Kamal, Marufa Rifat, Rakib Hossain Haque, Mohd Ariful George, Roy |
| contents | The black-box nature of Convolutional Neural Networks (CNNs) and their reliance on large datasets limit their use in complex domains with limited labeled data. Physics-Guided Neural Networks (PGNNs) have emerged to address these limitations by integrating scientific principles and real-world knowledge, enhancing model interpretability and efficiency. This paper proposes a novel Physics-Guided CNN (PGCNN) architecture that incorporates dynamic, trainable, and automated LLM-generated, widely recognized rules integrated into the model as custom layers to address challenges like limited data and low confidence scores. The PGCNN is evaluated on multiple datasets, demonstrating superior performance compared to a baseline CNN model. Key improvements include a significant reduction in false positives and enhanced confidence scores for true detection. The results highlight the potential of PGCNNs to improve CNN performance for broader application areas. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02081 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Physical Rule-Guided Convolutional Neural Network Gupta, Kishor Datta Kamal, Marufa Rifat, Rakib Hossain Haque, Mohd Ariful George, Roy Computer Vision and Pattern Recognition The black-box nature of Convolutional Neural Networks (CNNs) and their reliance on large datasets limit their use in complex domains with limited labeled data. Physics-Guided Neural Networks (PGNNs) have emerged to address these limitations by integrating scientific principles and real-world knowledge, enhancing model interpretability and efficiency. This paper proposes a novel Physics-Guided CNN (PGCNN) architecture that incorporates dynamic, trainable, and automated LLM-generated, widely recognized rules integrated into the model as custom layers to address challenges like limited data and low confidence scores. The PGCNN is evaluated on multiple datasets, demonstrating superior performance compared to a baseline CNN model. Key improvements include a significant reduction in false positives and enhanced confidence scores for true detection. The results highlight the potential of PGCNNs to improve CNN performance for broader application areas. |
| title | Physical Rule-Guided Convolutional Neural Network |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.02081 |