Interpretable Deep Convolutional Fuzzy Classifier

Yeganejou, Mojtaba; Dick, Scott; Miller, James

doi:10.1109/tfuzz.2019.2946520

Cited by 35 publications

(14 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the authors of (Deng et al 2017 ) presented an FDNN for classification tasks, such as natural scene image categorization and stock trend prediction. Similar studies for image classification can be found in (Guan et al 2020 ; Kunchala et al 2020 ; Liu et al 2020a , b ; Liu et al 2020a , b ; Manchanda et al 2020 ; Tianyu and Xu 2020 ; Yeganejou and Dick 2018 , 2019 ; Yeganejou et al 2020 ; Zhang et al 2020a , b , c ).…”

Section: Analysis and Synthesis Of Datasupporting

confidence: 69%

“…A simple example of a cooperative DNFS was proposed by (Yeganejou et al 2020 ) using a CNN for feature extraction and by transferring the outputs of the final convolutional layer for fuzzy classification, as depicted in Fig. 12 .…”

Section: Analysis and Synthesis Of Datamentioning

confidence: 99%

“…Next, a PCA-based dimension reduction idea is employed using GK clustering, in which a matrix inversion requires a step with each chosen feature map providing 196 features of a 14 × 14 image. Fuzzy clustering was executed, and Rocchio’s algorithm (Yeganejou et al 2020 ) (presented in Fig. 13 ) was employed as a classifier.…”

Section: Analysis and Synthesis Of Datamentioning

confidence: 99%

See 2 more Smart Citations

Deep Neuro-Fuzzy System application trends, challenges, and future perspectives: a systematic survey

et al. 2022

View full text Add to dashboard Cite

Deep neural networks (DNN) have remarkably progressed in applications involving large and complex datasets but have been criticized as a black-box. This downside has recently become a motivation for the research community to pursue the ideas of hybrid approaches, resulting in novel hybrid systems classified as deep neuro-fuzzy systems (DNFS). Studies regarding the implementation of DNFS have rapidly increased in the domains of computing, healthcare, transportation, and finance with high interpretability and reasonable accuracy. However, relatively few survey studies have been found in the literature to provide a comprehensive insight into this domain. Therefore, this study aims to perform a systematic review to evaluate the current progress, trends, arising issues, research gaps, challenges, and future scope related to DNFS studies. A study mapping process was prepared to guide a systematic search for publications related to DNFS published between 2015 and 2020 using five established scientific directories. As a result, a total of 105 studies were identified and critically analyzed to address research questions with the objectives: (i) to understand the concept of DNFS; (ii) to find out DNFS optimization methods; (iii) to visualize the intensity of work carried out in DNFS domain; and (iv) to highlight DNFS application subjects and domains. We believe that this study provides up-to-date guidance for future research in the DNFS domain, allowing for more effective advancement in techniques and processes. The analysis made in this review proves that DNFS-based research is actively growing with a substantial implementation and application scope in the future.

show abstract

Section: Analysis and Synthesis Of Datasupporting

confidence: 69%

Section: Analysis and Synthesis Of Datamentioning

confidence: 99%

Section: Analysis and Synthesis Of Datamentioning

confidence: 99%

See 1 more Smart Citation

Deep Neuro-Fuzzy System application trends, challenges, and future perspectives: a systematic survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Indeed, in many situations we do not need to trade accuracy for interpretability, as we can construct interpretable ML models that match or surpass accuracy of black-box models [8]. Fuzzy XAI has recently gained popularity in various applications [10]. Especially in safety critical applications, interpretable architectures are preferred over non-interpretable structures [5].…”

Section: Introductionmentioning

confidence: 99%

Takagi-Sugeno Fuzzy Systems with Triangular Membership Functions as Interpretable Neural Networks

Bede

Williams

2021

Explainable AI and Other Applications of Fuzzy Techniques

View full text Add to dashboard Cite

Equivalence between Neural Networks with ReLU activation and Takagi-Sugeno fuzzy systems with triangular membership functions is studied. We prove an equivalence relation between the above mentioned systems under relaxed conditions. As the above proofs are constructive, this method allows us to transform between the considered Neural Networks and Takagi-Sugeno systems. The interpretability of the proposed system is discussed and future research directions are explored.

show abstract

“…Some models visualized feature maps and filters in different layers like in NIN [48], SAD/FAD [53], CAR [66]. Other models visualized class activation maps to evaluate the class discrimination like Dynamic-K [52], XCNN [59], ProtoPNet [56], FBI [54], FCM [61], Loss Attention [45], SENN [63], Subnetwork Extraction [65], CAM [77], Grad-CAM [18], Grad-CAM++ [78], Smooth Grad-CAM++ [79], Augmented Grad-CAM [81], Score-CAM [22], IBD [84], Hpnet [87], U-CAM [82]. Additionally, saliency maps were visualized to reconstruct the input image based on the pixels/features influence on the CNN decision like in Integrated Gradients [72], FER-CNN [74], LRP [71], DeepLIFT [73], Saliency Maps [75], Deconv [76],…”

Section: Visualizationmentioning

confidence: 99%

Effective Explainable Artificial Intelligence using Visual Explanations in Images

Ibrahim¹

View full text Add to dashboard Cite

I would like to thank my advisor Professor. Omair Shafiq for his extraordinary support during my graduate study. Over the last six years, I have known Prof. Omair to be extremely helpful, caring, and resourceful. His exceptional mentorship allowed me to complete my master's degree and make remarkable progress in my Ph.D. studies. Because ofProf. Omair's extraordinary dedication and support, I could present my research, and publish 10 research papers in top conferences and journals like Springer Journal of Big Data, IEEE BigData, IEEE HPCC, and many more conferences. With his exceptional guidance, I was able to make excellent progress in my research and was able to receive several research scholarships and awards, including Ontario Graduate Scholarship (OGS) multiple times, The Queen Elizabeth II Scholarship in Science and Technology (QEII), Natural Sciences and Engineering Research Council of Canada (NSERC) Canada Graduate Scholarship for Master's (CGS-M), and finally Alexander Graham Bell Canada Graduate Scholarship (NSERC-CGS). Professor. Omair has truly inspired me to stay motivated toward my academic goals and bring out the best of my work. His encouragement helped me keep my progress even during the tough times of the COVID-19 pandemic. His optimism relaxed me and made me feel the light at the end of the tunnel. Without his exceptional guidance, commitment, determination, passion, and care, I could not have finished my Ph.D. research. Also, I want to present my gratitude to my deceased parents for their great sacrifices. Many thanks to my brothers, Hamid and Adham, for being true brothers when I needed them. Finally, I would like to express my deep thankfulness to my wife, Marwa, for her patience over the last six years. I could not be able to finish my research without her support. Author DeclarationI am the first author of the publications that have contributed to this thesis. The word 'we' is used in this document to indicate the collaboration with my supervisor on finishing these projects. I want to thank my supervisor, Dr. Omair Shafiq, for his support in achieving this work.Publications related to this thesis include:• Augmented Score-CAM: High resolution visual interpretations for deep neural networks.Elsevier Knowledge-Based Systems Journal. Published.

show abstract

Interpretable Deep Convolutional Fuzzy Classifier

Cited by 35 publications

References 49 publications

Deep Neuro-Fuzzy System application trends, challenges, and future perspectives: a systematic survey

Deep Neuro-Fuzzy System application trends, challenges, and future perspectives: a systematic survey

Takagi-Sugeno Fuzzy Systems with Triangular Membership Functions as Interpretable Neural Networks

Effective Explainable Artificial Intelligence using Visual Explanations in Images

Contact Info

Product

Resources

About