loss function
Recently Published Documents





2022 ◽  
Vol 16 (4) ◽  
pp. 1-21
Honghui Xu ◽  
Zhipeng Cai ◽  
Wei Li

Multi-label image recognition has been an indispensable fundamental component for many real computer vision applications. However, a severe threat of privacy leakage in multi-label image recognition has been overlooked by existing studies. To fill this gap, two privacy-preserving models, Privacy-Preserving Multi-label Graph Convolutional Networks (P2-ML-GCN) and Robust P2-ML-GCN (RP2-ML-GCN), are developed in this article, where differential privacy mechanism is implemented on the model’s outputs so as to defend black-box attack and avoid large aggregated noise simultaneously. In particular, a regularization term is exploited in the loss function of RP2-ML-GCN to increase the model prediction accuracy and robustness. After that, a proper differential privacy mechanism is designed with the intention of decreasing the bias of loss function in P2-ML-GCN and increasing prediction accuracy. Besides, we analyze that a bounded global sensitivity can mitigate excessive noise’s side effect and obtain a performance improvement for multi-label image recognition in our models. Theoretical proof shows that our two models can guarantee differential privacy for model’s outputs, weights and input features while preserving model robustness. Finally, comprehensive experiments are conducted to validate the advantages of our proposed models, including the implementation of differential privacy on model’s outputs, the incorporation of regularization term into loss function, and the adoption of bounded global sensitivity for multi-label image recognition.

2022 ◽  
Vol 40 (1) ◽  
pp. 1-30
Wanyu Chen ◽  
Pengjie Ren ◽  
Fei Cai ◽  
Fei Sun ◽  
Maarten De Rijke

Sequential recommenders capture dynamic aspects of users’ interests by modeling sequential behavior. Previous studies on sequential recommendations mostly aim to identify users’ main recent interests to optimize the recommendation accuracy; they often neglect the fact that users display multiple interests over extended periods of time, which could be used to improve the diversity of lists of recommended items. Existing work related to diversified recommendation typically assumes that users’ preferences are static and depend on post-processing the candidate list of recommended items. However, those conditions are not suitable when applied to sequential recommendations. We tackle sequential recommendation as a list generation process and propose a unified approach to take accuracy as well as diversity into consideration, called multi-interest, diversified, sequential recommendation . Particularly, an implicit interest mining module is first used to mine users’ multiple interests, which are reflected in users’ sequential behavior. Then an interest-aware, diversity promoting decoder is designed to produce recommendations that cover those interests. For training, we introduce an interest-aware, diversity promoting loss function that can supervise the model to learn to recommend accurate as well as diversified items. We conduct comprehensive experiments on four public datasets and the results show that our proposal outperforms state-of-the-art methods regarding diversity while producing comparable or better accuracy for sequential recommendation.

2022 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Yang Yi ◽  
Yang Sun ◽  
Saimei Yuan ◽  
Yiji Zhu ◽  
Mengyi Zhang ◽  

Purpose The purpose of this paper is to provide a fast and accurate network for spatiotemporal action localization in videos. It detects human actions both in time and space simultaneously in real-time, which is applicable in real-world scenarios such as safety monitoring and collaborative assembly. Design/methodology/approach This paper design an end-to-end deep learning network called collaborator only watch once (COWO). COWO recognizes the ongoing human activities in real-time with enhanced accuracy. COWO inherits from the architecture of you only watch once (YOWO), known to be the best performing network for online action localization to date, but with three major structural modifications: COWO enhances the intraclass compactness and enlarges the interclass separability in the feature level. A new correlation channel fusion and attention mechanism are designed based on the Pearson correlation coefficient. Accordingly, a correction loss function is designed. This function minimizes the same class distance and enhances the intraclass compactness. Use a probabilistic K-means clustering technique for selecting the initial seed points. The idea behind this is that the initial distance between cluster centers should be as considerable as possible. CIOU regression loss function is applied instead of the Smooth L1 loss function to help the model converge stably. Findings COWO outperforms the original YOWO with improvements of frame mAP 3% and 2.1% at a speed of 35.12 fps. Compared with the two-stream, T-CNN, C3D, the improvement is about 5% and 14.5% when applied to J-HMDB-21, UCF101-24 and AGOT data sets. Originality/value COWO extends more flexibility for assembly scenarios as it perceives spatiotemporal human actions in real-time. It contributes to many real-world scenarios such as safety monitoring and collaborative assembly.

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 656
Jingyi Liu ◽  
Shuni Song ◽  
Jiayi Wang ◽  
Maimutimin Balaiti ◽  
Nina Song ◽  

With the improvement of industrial requirements for the quality of cold rolled strips, flatness has become one of the most important indicators for measuring the quality of cold rolled strips. In this paper, the strip production data of a 1250 mm tandem cold mill in a steel plant is modeled by an improved deep neural network (the improved DNN) to improve the accuracy of strip shape prediction. Firstly, the type of activation function is analyzed, and the monotonicity of the activation function is deemed independent of the convexity of the loss function in the deep network. Regardless of whether the activation function is monotonic, the loss function is not strictly convex. Secondly, the non-convex optimization of the loss functionextended from the deep linear network to the deep nonlinear network, is discussed, and the critical point of the deep nonlinear network is identified as the global minimum point. Finally, an improved Swish activation function based on batch normalization is proposed, and its performance is evaluated on the MNIST dataset. The experimental results show that the loss of an improved Swish function is lower than that of other activation functions. The prediction accuracy of a deep neural network (DNN) with an improved Swish function is 0.38% more than that of a deep neural network (DNN) with a regular Swish function. For the DNN with the improved Swish function, the mean square error of the prediction for the flatness of cold rolled strip is reduced to 65% of the regular DNN. The accuracy of the improved DNN is up to and higher than the industrial requirements. The shape prediction of the improved DNN will assist and guide the industrial production process, reducing the scrap yield and industrial cost.

Life ◽  
2022 ◽  
Vol 12 (1) ◽  
pp. 119
Hengyang Fang ◽  
Changhua Lu ◽  
Feng Hong ◽  
Weiwei Jiang ◽  
Tao Wang

Aiming at the fact that traditional convolutional neural networks cannot effectively extract signal features in complex application scenarios, a sleep apnea (SA) detection method based on multi-scale residual networks is proposed. First, we analyze the physiological mechanism of SA, which uses the RR interval signals and R peak signals derived from the ECG signals as input. Then, a multi-scale residual network is used to extract the characteristics of the original signals in order to obtain sensitive characteristics from various angles. Because the residual structure is used in the model, the problem of model degradation can be avoided. Finally, a fully connected layer is introduced for SA detection. In order to overcome the impact of class imbalance, a focal loss function is introduced to replace the traditional cross-entropy loss function, which makes the model pay more attention to learning difficult samples in the training phase. Experimental results from the Apnea-ECG dataset show that the accuracy, sensitivity and specificity of the proposed multi-scale residual network are 86.0%, 84.1% and 87.1%, respectively. These results indicate that the proposed method not only achieves greater recognition accuracy than other methods, but it also effectively resolves the problem of low sensitivity caused by class imbalance.

2022 ◽  
Syed Awais Rouf ◽  
Muhammad Iqbal Hussain ◽  
Umair Mumtaz ◽  
Hafiz Tariq Masood ◽  
Hind Albalawi ◽  

Abstract The ab-initio computations were performed to study the electronic and optoelectronic properties of RhXO3 (X = Ga, Ag) using WIEN2k code. The RhGaO3 has band gap of 2.29 eV, and the behavior of RhAgO3 metallic. The sub-TDOS of the studied materials revealed that rhodium and oxygen atoms have significant contributions in the valence band and conduction band formation of both materials. The silver cation is responsible for the reasonable peaks appearing at the Fermi level of RhAgO3, which demonstrated the conducting nature of RhAgO3. The dielectric functions, optical conductivity, energy loss function, absorption coefficient, refractive index, extinction coefficient, and reflectivity are computed for these materials to understand the optical behavior of the studied materials. The analysis of optical properties ensure the RhGaO3 is a promising material for optoelectronics while RhAgO3 has metallic nature.

Information ◽  
2022 ◽  
Vol 13 (1) ◽  
pp. 32
Gang Sun ◽  
Hancheng Yu ◽  
Xiangtao Jiang ◽  
Mingkui Feng

Edge detection is one of the fundamental computer vision tasks. Recent methods for edge detection based on a convolutional neural network (CNN) typically employ the weighted cross-entropy loss. Their predicted results being thick and needing post-processing before calculating the optimal dataset scale (ODS) F-measure for evaluation. To achieve end-to-end training, we propose a non-maximum suppression layer (NMS) to obtain sharp boundaries without the need for post-processing. The ODS F-measure can be calculated based on these sharp boundaries. So, the ODS F-measure loss function is proposed to train the network. Besides, we propose an adaptive multi-level feature pyramid network (AFPN) to better fuse different levels of features. Furthermore, to enrich multi-scale features learned by AFPN, we introduce a pyramid context module (PCM) that includes dilated convolution to extract multi-scale features. Experimental results indicate that the proposed AFPN achieves state-of-the-art performance on the BSDS500 dataset (ODS F-score of 0.837) and the NYUDv2 dataset (ODS F-score of 0.780).

Symmetry ◽  
2022 ◽  
Vol 14 (1) ◽  
pp. 132
Jianfeng Zheng ◽  
Shuren Mao ◽  
Zhenyu Wu ◽  
Pengcheng Kong ◽  
Hao Qiang

To solve the problems of poor exploration ability and convergence speed of traditional deep reinforcement learning in the navigation task of the patrol robot under indoor specified routes, an improved deep reinforcement learning algorithm based on Pan/Tilt/Zoom(PTZ) image information was proposed in this paper. The obtained symmetric image information and target position information are taken as the input of the network, the speed of the robot is taken as the output of the next action, and the circular route with boundary is taken as the test. The improved reward and punishment function is designed to improve the convergence speed of the algorithm and optimize the path so that the robot can plan a safer path while avoiding obstacles first. Compared with Deep Q Network(DQN) algorithm, the convergence speed after improvement is shortened by about 40%, and the loss function is more stable.

2022 ◽  
pp. 1-29
Yancheng Lv ◽  
Lin Lin ◽  
Jie Liu ◽  
Hao Guo ◽  
Changsheng Tong

Abstract Most of the research on machine learning classification methods is based on balanced data; the research on imbalanced data classification needs improvement. Generative adversarial networks (GANs) are able to learn high-dimensional complex data distribution without relying on a prior hypothesis, which has become a hot technology in artificial intelligence. In this letter, we propose a new structure, classroom-like generative adversarial networks (CLGANs), to construct a model with multiple generators. Taking inspiration from the fact that teachers arrange teaching activities according to students' learning situation, we propose a weight allocation function to adaptively adjust the influence weight of generator loss function on discriminator loss function. All the generators work together to improve the degree of discriminator and training sample space, so that a discriminator with excellent performance is trained and applied to the tasks of imbalanced data classification. Experimental results on the Case Western Reserve University data set and 2.4 GHz Indoor Channel Measurements data set show that the data classification ability of the discriminator trained by CLGANs with multiple generators is superior to that of other imbalanced data classification models, and the optimal discriminator can be obtained by selecting the right matching scheme of the generator models.

Maximilian Paul Niroomand ◽  
Conor T Cafolla ◽  
John William Roger Morgan ◽  
David J Wales

Abstract One of the most common metrics to evaluate neural network classifiers is the area under the receiver operating characteristic curve (AUC). However, optimisation of the AUC as the loss function during network training is not a standard procedure. Here we compare minimising the cross-entropy (CE) loss and optimising the AUC directly. In particular, we analyse the loss function landscape (LFL) of approximate AUC (appAUC) loss functions to discover the organisation of this solution space. We discuss various surrogates for AUC approximation and show their differences. We find that the characteristics of the appAUC landscape are significantly different from the CE landscape. The approximate AUC loss function improves testing AUC, and the appAUC landscape has substantially more minima, but these minima are less robust, with larger average Hessian eigenvalues. We provide a theoretical foundation to explain these results. To generalise our results, we lastly provide an overview of how the LFL can help to guide loss function analysis and selection.

Sign in / Sign up

Export Citation Format

Share Document