Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Samek, Wojciech; Montavon, Grégoire; Lapuschkin, Sebastian; Anders, Christopher J.; Müller, Klaus‐Robert

doi:10.1109/jproc.2021.3060483

Cited by 803 publications

(418 citation statements)

References 140 publications

(249 reference statements)

Supporting

Mentioning

409

Contrasting

Unclassified

Order By: Relevance

“…The results of Constantin et al show that the teaching scheme of group online education in colleges and universities has good teaching effect, which is suitable for the online education of junior and senior students [ 16 ]. To sum up, it can be seen that most of the current online education classroom teaching modes in colleges and universities do not involve the intelligent algorithm based on the difference of the characteristics of the student group [ 17 ]. There are relatively few research results on specific quantitative dynamic evaluation system and quality evaluation of online education classroom teaching [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Optimization of Online Education and Teaching Evaluation System Based on GA‐BP Neural Network

Feng-hu

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the popularization and application of online education in the world, how to evaluate and analyze the classroom teaching effect through scientific methods has become one of the important teaching tasks in colleges. Based on this, this paper studies the application of the GA-BP neural network algorithm. Firstly, it gives a brief overview of the current situation of online education and GA-BP neural network algorithm. Secondly, through the investigation of the online education system in many aspects, it evaluates students’ online education classroom teaching quality from five aspects, and this paper proposes a more scientific online education classroom teaching quality evaluation optimization model and finally verifies the reliability of the online education teaching evaluation model through the practice in a university. The results show that the GA-BP neural network-based evaluation optimization model can effectively evaluate the online education in the process of analyzing the quality of online education classroom teaching of most professional students.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] Optimization of Online Education and Teaching Evaluation System Based on GA‐BP Neural Network

Feng-hu

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…In the last few years, many papers concerning deep neural networks have been published [21][22][23][24][25][26][27]. Most of them concern the development of deep neural architectures for detecting objects in images; however, we will limit our discussion to the state of art architectures.…”

Section: Related Workmentioning

confidence: 99%

Application of Deep Learning Networks to Segmentation of Surface of Railway Tracks

Bojarczak

Nowakowski

2021

Sensors

View full text Add to dashboard Cite

The article presents a vision system for detecting elements of railway track. Four types of fasteners, wooden and concrete sleepers, rails, and turnouts can be recognized by our system. In addition, it is possible to determine the degree of sleeper ballast coverage. Our system is also able to work when the track is moderately covered by snow. We used a Fully Convolutional Neural Network with 8 times upsampling (FCN-8) to detect railway track elements. In order to speed up training and improve performance of the model, a pre-trained deep convolutional neural network developed by Oxford’s Visual Geometry Group (VGG16) was used as a framework for our system. We also verified the invariance of our system to changes in brightness. To do this, we artificially varied the brightness of images. We performed two types of tests. In the first test, we changed the brightness by a constant value for the whole analyzed image. In the second test, we changed the brightness according to a predefined distribution corresponding to Gaussian function.

show abstract

“…Algorithms based on ANNs have shown a great success in modeling both the linear and the non-linear relationships in the underlying data. Due to a huge success rate of these algorithms, they are extensively being used for different real-time applications [1]- [4]. Moreover, with an increase in the availability of huge datasets, the deep learning models have specifically shown a significant improvement in the classification of videos.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Video Classification: A Review

Rehman¹,

Belhaouari²

2021

Preprint

View full text Add to dashboard Cite

<div><div><div><p>Video classification task has gained a significant success in the recent years. Specifically, the topic has gained more attention after the emergence of deep learning models as a successful tool for automatically classifying videos. In recognition to the importance of video classification task and to summarize the success of deep learning models for this task, this paper presents a very comprehensive and concise review on the topic. There are a number of existing reviews and survey papers related to video classification in the scientific literature. However, the existing review papers are either outdated, and therefore, do not include the recent state-of-art works or they have some limitations. In order to provide an updated and concise review, this paper highlights the key findings based on the existing deep learning models. The key findings are also discussed in a way to provide future research directions. This review mainly focuses on the type of network architecture used, the evaluation criteria to measure the success, and the data sets used. To make the review self- contained, the emergence of deep learning methods towards automatic video classification and the state-of-art deep learning methods are well explained and summarized. Moreover, a clear insight of the newly developed deep learning architectures and the traditional approaches is provided, and the critical challenges based on the benchmarks are highlighted for evaluating the technical progress of these methods. The paper also summarizes the benchmark datasets and the performance evaluation matrices for video classification. Based on the compact, complete, and concise review, the paper proposes new research directions to solve the challenging video classification problem.</p></div></div></div>

show abstract

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Abstract: This review provides a timely overview of explainable AI for deep neural networks, with a focus on post hoc explanations.

Cited by 803 publications

References 140 publications

[Retracted] Optimization of Online Education and Teaching Evaluation System Based on GA‐BP Neural Network

[Retracted] Optimization of Online Education and Teaching Evaluation System Based on GA‐BP Neural Network

Application of Deep Learning Networks to Segmentation of Surface of Railway Tracks

Deep Learning for Video Classification: A Review

Contact Info

Product

Resources

About