DCNFIS: Deep Convolutional Neuro-Fuzzy Inference System
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917615733047296 |
|---|---|
| author | Yeganejou, Mojtaba Honari, Kimia Kluzinski, Ryan Dick, Scott Lipsett, Michael Miller, James |
| author_facet | Yeganejou, Mojtaba Honari, Kimia Kluzinski, Ryan Dick, Scott Lipsett, Michael Miller, James |
| contents | A key challenge in eXplainable Artificial Intelligence is the well-known tradeoff between the transparency of an algorithm (i.e., how easily a human can directly understand the algorithm, as opposed to receiving a post-hoc explanation), and its accuracy. We report on the design of a new deep network that achieves improved transparency without sacrificing accuracy. We design a deep convolutional neuro-fuzzy inference system (DCNFIS) by hybridizing fuzzy logic and deep learning models and show that DCNFIS performs as accurately as existing convolutional neural networks on four well-known datasets and 3 famous architectures. Our performance comparison with available fuzzy methods show that DCNFIS is now state-of-the-art fuzzy system and outperforms other shallow and deep fuzzy methods to the best of our knowledge. At the end, we exploit the transparency of fuzzy logic by deriving explanations, in the form of saliency maps, from the fuzzy rules encoded in the network to take benefit of fuzzy logic upon regular deep learning methods. We investigate the properties of these explanations in greater depth using the Fashion-MNIST dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_06378 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DCNFIS: Deep Convolutional Neuro-Fuzzy Inference System Yeganejou, Mojtaba Honari, Kimia Kluzinski, Ryan Dick, Scott Lipsett, Michael Miller, James Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning A key challenge in eXplainable Artificial Intelligence is the well-known tradeoff between the transparency of an algorithm (i.e., how easily a human can directly understand the algorithm, as opposed to receiving a post-hoc explanation), and its accuracy. We report on the design of a new deep network that achieves improved transparency without sacrificing accuracy. We design a deep convolutional neuro-fuzzy inference system (DCNFIS) by hybridizing fuzzy logic and deep learning models and show that DCNFIS performs as accurately as existing convolutional neural networks on four well-known datasets and 3 famous architectures. Our performance comparison with available fuzzy methods show that DCNFIS is now state-of-the-art fuzzy system and outperforms other shallow and deep fuzzy methods to the best of our knowledge. At the end, we exploit the transparency of fuzzy logic by deriving explanations, in the form of saliency maps, from the fuzzy rules encoded in the network to take benefit of fuzzy logic upon regular deep learning methods. We investigate the properties of these explanations in greater depth using the Fashion-MNIST dataset. |
| title | DCNFIS: Deep Convolutional Neuro-Fuzzy Inference System |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2308.06378 |