Handling Vanishing Gradient Problem Using Artificial Derivative

Hu, Zheng; Zhang, Jiaojiao; Ge, Yun

doi:10.1109/access.2021.3054915

Cited by 52 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The selected model implements DNN with hidden LSTM layers ( Figure 7 ). We used the rectified linear activation function (ReLu), since it overcomes the vanishing gradient problems present in RNNs [ 46 , 47 ]. It also allows models to learn faster and perform better.…”

Section: Methodsmentioning

confidence: 99%

Towards a Safe Human–Robot Collaboration Using Information on Human Worker Activity

Orsag

Stipančić

Koren

2023

Sensors

View full text Add to dashboard Cite

Most industrial workplaces involving robots and other apparatus operate behind the fences to remove defects, hazards, or casualties. Recent advancements in machine learning can enable robots to co-operate with human co-workers while retaining safety, flexibility, and robustness. This article focuses on the computation model, which provides a collaborative environment through intuitive and adaptive human–robot interaction (HRI). In essence, one layer of the model can be expressed as a set of useful information utilized by an intelligent agent. Within this construction, a vision-sensing modality can be broken down into multiple layers. The authors propose a human-skeleton-based trainable model for the recognition of spatiotemporal human worker activity using LSTM networks, which can achieve a training accuracy of 91.365%, based on the InHARD dataset. Together with the training results, results related to aspects of the simulation environment and future improvements of the system are discussed. By combining human worker upper body positions with actions, the perceptual potential of the system is increased, and human–robot collaboration becomes context-aware. Based on the acquired information, the intelligent agent gains the ability to adapt its behavior according to its dynamic and stochastic surroundings.

show abstract

Section: Methodsmentioning

confidence: 99%

Towards a Safe Human–Robot Collaboration Using Information on Human Worker Activity

Orsag

Stipančić

Koren

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The ReLU expedites the training and avoids the vanishing gradient [ 49 ]. The last layer in the network is called the output layer (classification layer), which gives the probability of occurrence of different classes.…”

Section: Methodsmentioning

confidence: 99%

Multiclass Cancer Prediction Based on Copy Number Variation Using Deep Learning

Attique

Shah

Jabeen³

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

DNA copy number variation (CNV) is the type of DNA variation which is associated with various human diseases. CNV ranges in size from 1 kilobase to several megabases on a chromosome. Most of the computational research for cancer classification is traditional machine learning based, which relies on handcrafted extraction and selection of features. To the best of our knowledge, the deep learning-based research also uses the step of feature extraction and selection. To understand the difference between multiple human cancers, we developed three end-to-end deep learning models, i.e., DNN (fully connected), CNN (convolution neural network), and RNN (recurrent neural network), to classify six cancer types using the CNV data of 24,174 genes. The strength of an end-to-end deep learning model lies in representation learning (automatic feature extraction). The purpose of proposing more than one model is to find which architecture among them performs better for CNV data. Our best model achieved 92% accuracy with an ROC of 0.99, and we compared the performances of our proposed models with state-of-the-art techniques. Our models have outperformed the state-of-the-art techniques in terms of accuracy, precision, and ROC. In the future, we aim to work on other types of cancers as well.

show abstract

“…In this network, the earliest layers of the design employ depth-wise separable convolutions to speed up the calculations involved in down sampling the input pictures. In order to increase convergence during training, they also devised a batch normalization layer that may reduce internal covariate shift and address the gradient vanishing problem [31]. ResNet50 is a slimmer iteration of ResNet101, which took first place in the ILSVRC classification challenge.…”

Section: Methodsmentioning

confidence: 99%

Development of Automatic Segmentation Techniques using Convolutional Neural Networks to Differentiate Diabetic Foot Ulcers

Prakash¹,

Kumar²

2022

IJACSA

View full text Add to dashboard Cite

The quality of computer vision systems to detect abnormalities in various medical imaging processes, such as dual-energy X-ray absorptiometry, magnetic resonance imaging (MRI), ultrasonography, and computed tomography, has significantly improved as a result of recent developments in the field of deep learning. There is discussion of current techniques and algorithms for identifying, categorizing, and detecting DFU. On the small datasets, a variety of techniques based on traditional machine learning and image processing are utilized to find the DFU. These literary works have kept their datasets and algorithms private. Therefore, the need for end-to-end automated systems that can identify DFU of all grades and stages is critical. The study's goals were to create new CNN-based automatic segmentation techniques to separate surrounding skin from DFU on full foot images because surrounding skin serves as a critical visual cue for evaluating the progression of DFU as well as to create reliable and portable deep learning techniques for localizing DFU that can be applied to mobile devices for remote monitoring. The second goal was to examine the various diabetic foot diseases in accordance with well-known medical categorization schemes. According to a computer vision viewpoint, the authors looked at the various DFU circumstances including site, infection, neuropathy, bacterial infection, area, and depth. Machine learning techniques have been utilized in this study to identify key DFU situations as ischemia and bacterial infection.

show abstract

Handling Vanishing Gradient Problem Using Artificial Derivative

Cited by 52 publications

References 7 publications

Towards a Safe Human–Robot Collaboration Using Information on Human Worker Activity

Towards a Safe Human–Robot Collaboration Using Information on Human Worker Activity

Multiclass Cancer Prediction Based on Copy Number Variation Using Deep Learning

Development of Automatic Segmentation Techniques using Convolutional Neural Networks to Differentiate Diabetic Foot Ulcers

Contact Info

Product

Resources

About