Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Buhrmester, Vanessa; Münch, David; Arens, Michael

doi:10.3390/make3040048

Cited by 186 publications

(90 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Essentially neural networks are non-linear mappings with many parameters. Due to a large number of parameters, they are referred to as a "black-box" [6]. A loss function is defined to measure the difference between the output of the network with the known (expected) output.…”

Section: Input Layermentioning

confidence: 99%

Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks

Wight¹,

Zhao

2020

Preprint

View full text Add to dashboard Cite

Phase field models, in particular, the Allen-Cahn type and Cahn-Hilliard type equations, have been widely used to investigate interfacial dynamic problems. Designing accurate, efficient, and stable numerical algorithms for solving the phase field models has been an active field for decades. In this paper, we focus on using the deep neural network to design an automatic numerical solver for the Allen-Cahn and Cahn-Hilliard equations by proposing an improved physics informed neural network (PINN). Though the PINN has been embraced to investigate many differential equation problems, we find a direct application of the PINN in solving phase-field equations won't provide accurate solutions in many cases. Thus, we propose various techniques that add to the approximation power of the PINN. As a major contribution of this paper, we propose to embrace the adaptive idea in both space and time and introduce various sampling strategies, such that we are able to improve the efficiency and accuracy of the PINN on solving phase field equations. In addition, the improved PINN has no restriction on the explicit form of the PDEs, making it applicable to a wider class of PDE problems, and shedding light on numerical approximations of other PDEs in general.

show abstract

Section: Input Layermentioning

confidence: 99%

Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks

Wight¹,

Zhao

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The synaptic weight informs about the amplitude or the strength of the connection between two nodes (neurons). Since ANNs are black-box models because of their multilayer nonlinear structure, the explanation of the underlying process that produces the relationship between the dependent (target) and independent (predictors) variables is unintelligible, nontransparent, and untraceable by humans [ 30 ]. The overall survival outcome and the molecular subtypes of patients with diffuse large B-cell lymphoma (DLBCL) were predicted with high accuracy, and the most relevant genes were highlighted using nonlinear analysis.…”

Section: Discussionmentioning

confidence: 99%

Artificial Neural Networks Predicted the Overall Survival and Molecular Subtypes of Diffuse Large B-Cell Lymphoma Using a Pancancer Immune-Oncology Panel

Carreras

Hiraiwa

Kikuti

et al. 2021

Cancers

View full text Add to dashboard Cite

Diffuse large B-cell lymphoma (DLBCL) is one of the most frequent subtypes of non-Hodgkin lymphomas. We used artificial neural networks (multilayer perceptron and radial basis function), machine learning, and conventional bioinformatics to predict the overall survival and molecular subtypes of DLBCL. The series included 106 cases and 730 genes of a pancancer immune oncology panel (nCounter) as predictors. The multilayer perceptron predicted the outcome with high accuracy, with an area under the curve (AUC) of 0.98, and ranked all the genes according to their importance. In a multivariate analysis, ARG1, TNFSF12, REL, and NRP1 correlated with favorable survival (hazard risks: 0.3–0.5), and IFNA8, CASP1, and CTSG, with poor survival (hazard risks = 1.0–2.1). Gene set enrichment analysis (GSEA) showed enrichment toward poor prognosis. These high-risk genes were also associated with the gene expression of M2-like tumor-associated macrophages (CD163), and MYD88 expression. The prognostic relevance of this set of 7 genes was also confirmed within the IPI and MYC translocation strata, the EBER-negative cases, the DLBCL not-otherwise specified (NOS) (High-grade B-cell lymphoma with MYC and BCL2 and/or BCL6 rearrangements excluded), and an independent series of 414 cases of DLBCL in Europe and North America (GSE10846). The perceptron analysis also predicted molecular subtypes (based on the Lymph2Cx assay) with high accuracy (AUC = 1). STAT6, TREM2, and REL were associated with the germinal center B-cell (GCB) subtype, and CD37, GNLY, CD46, and IL17B were associated with the activated B-cell (ABC)/unspecified subtype. The GSEA had a sinusoidal-like plot with association to both molecular subtypes, and immunohistochemistry analysis confirmed the correlation of MAPK3 with the GCB subtype in another series of 96 cases (notably, MAPK3 also correlated with LMO2, but not with M2-like tumor-associated macrophage markers CD163, CSF1R, TNFAIP8, CASP8, PD-L1, PTX3, and IL-10). Finally, survival and molecular subtypes were successfully modeled using other machine learning techniques including logistic regression, discriminant analysis, SVM, CHAID, C5, C&R trees, KNN algorithm, and Bayesian network. In conclusion, prognoses and molecular subtypes were predicted with high accuracy using neural networks, and relevant genes were highlighted.

show abstract

“…Therefore, the DNN is defined as a "black box", mainly because there is no primary theoretical basis. Scholars divide the interpretability of the DNN into two types: post hoc interpretability and intrinsic interpretability [63,64]. The post hoc interpretability interprets the decisions in the actual application [65], in which the visualization method is the widely used approach [66].…”

Section: Characteristic Of the Dnn's Black Boxmentioning

confidence: 99%

SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation

Lin

Huang

Lin

et al. 2022

Sensors

View full text Add to dashboard Cite

Precipitation intensity estimation is a critical issue in the analysis of weather conditions. Most existing approaches focus on building complex models to extract rain streaks. However, an efficient approach to estimate the precipitation intensity from surveillance cameras is still challenging. This study proposes a convolutional neural network known as the signal filtering convolutional neural network (SF-CNN) to handle precipitation intensity using surveillance-based images. The SF-CNN has two main blocks, the signal filtering block (SF block) and the gradually decreasing dimension block (GDD block), to extract features for the precipitation intensity estimation. The SF block with the filtering operation is constructed in different parts of the SF-CNN to remove the noise from the features containing rain streak information. The GDD block continuously takes the pair of the convolutional operation with the activation function to reduce the dimension of features. Our main contributions are (1) an SF block considering the signal filtering process and effectively removing the useless signals and (2) a procedure of gradually decreasing the dimension of the feature able to learn and reserve the information of features. Experiments on the self-collected dataset, consisting of 9394 raining images with six precipitation intensity levels, demonstrate the proposed approach’s effectiveness against the popular convolutional neural networks. To the best of our knowledge, the self-collected dataset is the largest dataset for monitoring infrared images of precipitation intensity.

show abstract

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Cited by 186 publications

References 76 publications

Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks

Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks

Artificial Neural Networks Predicted the Overall Survival and Molecular Subtypes of Diffuse Large B-Cell Lymphoma Using a Pancancer Immune-Oncology Panel

SF-CNN: Signal Filtering Convolutional Neural Network for Precipitation Intensity Estimation

Contact Info

Product

Resources

About