Deep Residual Learning for Nonlinear Regression

Chen, Dongwei; Hu, Fei; Nian, Guokui; Yang, Tiantian

doi:10.3390/e22020193

Cited by 60 publications

(42 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ResNet introduced shortcut connection to train very deep convolutional models, with no extra parameters and no added computation complexity. For this nonlinear regression implementation, we replace the convolution layers by fully connected layers, as shown to work in [14].…”

Section: Model 2: Resnetregmentioning

confidence: 99%

Synthetic Q-Space Learning With Deep Regression Networks For Prostate Cancer Characterisation With Verdict

Valindria

Palombo

Chiou

et al. 2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

Traditional quantitative MRI (qMRI) signal model fitting to diffusion-weighted MRI (DW-MRI) is slow and requires long computational time per patient. Recently, q-space learning utilises machine learning methods to overcome these issues and to infer diffusion metrics. However, most of q-space learning studies use simple multi layer perceptron (MLP) for model fitting, which might be sub-optimal when estimating more complex diffusion models with many free parameters. Previous works only investigate the application of q-space learning on diffusion models in the brain. In this work, we explore q-space learning for prostate cancer characterization. Our results show that while simple MLP is adequate to estimate parametric maps on simple models like classic VER-DICT, deep residual regression networks are needed for more complex models such as VERDICT with compensated relaxation (R-VERDICT).

show abstract

Section: Model 2: Resnetregmentioning

confidence: 99%

Synthetic Q-Space Learning With Deep Regression Networks For Prostate Cancer Characterisation With Verdict

Valindria

Palombo

Chiou

et al. 2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

show abstract

“…We use a regression ResNet model (Chen et al, 2020) to predict the repulsive pose. The results in the study by Shi et al (2020) have shown that the MAEs of the model on the test set are less than 8.…”

Section: Repulsive Pose Predictionmentioning

confidence: 99%

“…We use a ResNet-based network for the regression task (Chen et al, 2020). The architecture of the network is shown in Figure 3.…”

Section: Resnet For Regressionmentioning

confidence: 99%

“…As indicated in our previous work (Shi et al, 2020), moving the TCP to a repulsive pose which is around the opposite repulsive pose can still avoid the collision with the hand, and the image moment error could be smaller than the opposite pose. We use a regression ResNet (He et al, 2016;Chen et al, 2020) to predict a repulsive position. In a study by Chen et al (2020), it is shown that using a ResNet for regression outperforms neural network (NN) and other conventional machine learning regression algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…We use a regression ResNet (He et al, 2016;Chen et al, 2020) to predict a repulsive position. In a study by Chen et al (2020), it is shown that using a ResNet for regression outperforms neural network (NN) and other conventional machine learning regression algorithms. As shown in Figure 1, we consider a quartersphere space around the robot TCP.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Bayesian Deep Neural Network for Safe Visual Servoing in Human–Robot Interaction

2021

View full text Add to dashboard Cite

Safety is an important issue in human–robot interaction (HRI) applications. Various research works have focused on different levels of safety in HRI. If a human/obstacle is detected, a repulsive action can be taken to avoid the collision. Common repulsive actions include distance methods, potential field methods, and safety field methods. Approaches based on machine learning are less explored regarding the selection of the repulsive action. Few research works focus on the uncertainty of the data-based approaches and consider the efficiency of the executing task during collision avoidance. In this study, we describe a system that can avoid collision with human hands while the robot is executing an image-based visual servoing (IBVS) task. We use Monte Carlo dropout (MC dropout) to transform a deep neural network (DNN) to a Bayesian DNN, and learn the repulsive position for hand avoidance. The Bayesian DNN allows IBVS to converge faster than the opposite repulsive pose. Furthermore, it allows the robot to avoid undesired poses that the DNN cannot avoid. The experimental results show that Bayesian DNN has adequate accuracy and can generalize well on unseen data. The predictive interval coverage probability (PICP) of the predictions along x, y, and z directions are 0.84, 0.94, and 0.95, respectively. In the space which is unseen in the training data, the Bayesian DNN is also more robust than a DNN. We further implement the system on a UR10 robot, and test the robustness of the Bayesian DNN and the IBVS convergence speed. Results show that the Bayesian DNN can avoid the poses out of the reach range of the robot and it lets the IBVS task converge faster than the opposite repulsive pose.1

show abstract