Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892978
Lorenzo Puppi Vecchi, E. C. F. Maffezzolli, E. Paraiso
Text style transfer is a relevant task, contributing to theoretical and practical advancement in several areas, especially when working with non-parallel data. The concept behind non-parallel style transfer is to change a specific dimension of the sentence while retaining the overall context. Previous work used adversarial learning to perform such a task. Although it was not initially created to work with textual data, it proved very effective. Most of the previous work has focused on developing algorithms capable of transferring between binary styles, with limited generalization capabilities and limited applications. This work proposes a framework capable of working with multiple styles and improving content retention (BLEU) after a transfer. The proposed framework combines supervised learning of latent spaces and their separation within the architecture. The results suggest that the proposed framework improves content retention in multi-style scenarios while maintaining accuracy comparable to state-of-the-art.
{"title":"Transferring multiple text styles using CycleGAN with supervised style latent space","authors":"Lorenzo Puppi Vecchi, E. C. F. Maffezzolli, E. Paraiso","doi":"10.1109/IJCNN55064.2022.9892978","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892978","url":null,"abstract":"Text style transfer is a relevant task, contributing to theoretical and practical advancement in several areas, especially when working with non-parallel data. The concept behind non-parallel style transfer is to change a specific dimension of the sentence while retaining the overall context. Previous work used adversarial learning to perform such a task. Although it was not initially created to work with textual data, it proved very effective. Most of the previous work has focused on developing algorithms capable of transferring between binary styles, with limited generalization capabilities and limited applications. This work proposes a framework capable of working with multiple styles and improving content retention (BLEU) after a transfer. The proposed framework combines supervised learning of latent spaces and their separation within the architecture. The results suggest that the proposed framework improves content retention in multi-style scenarios while maintaining accuracy comparable to state-of-the-art.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114755125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892669
Xiaohan Zou, Tong Lin
Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference trade-off problem between different examples. However, they still suffer from the catastrophic forgetting problem in the setting of continual learning, since the past data of previous tasks are no longer available. In this work, we propose a novel efficient meta-learning algorithm for solving the online continual learning problem, where the regularization terms and learning rates are adapted to the Taylor approximation of the parameter's importance to mitigate forgetting. The proposed method expresses the gradient of the meta-loss in closed-form and thus avoid computing second-order derivative which is computationally inhibitable. We also use Proximal Gradient Descent to further improve computational efficiency and accuracy. Experiments on diverse benchmarks show that our method achieves better or on-par performance and much higher efficiency compared to the state-of-the-art approaches.
{"title":"Efficient Meta-Learning for Continual Learning with Taylor Expansion Approximation","authors":"Xiaohan Zou, Tong Lin","doi":"10.1109/IJCNN55064.2022.9892669","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892669","url":null,"abstract":"Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference trade-off problem between different examples. However, they still suffer from the catastrophic forgetting problem in the setting of continual learning, since the past data of previous tasks are no longer available. In this work, we propose a novel efficient meta-learning algorithm for solving the online continual learning problem, where the regularization terms and learning rates are adapted to the Taylor approximation of the parameter's importance to mitigate forgetting. The proposed method expresses the gradient of the meta-loss in closed-form and thus avoid computing second-order derivative which is computationally inhibitable. We also use Proximal Gradient Descent to further improve computational efficiency and accuracy. Experiments on diverse benchmarks show that our method achieves better or on-par performance and much higher efficiency compared to the state-of-the-art approaches.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124301889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, object tracking techniques based on Siamese networks have shown excellent tracking performance. However, in the tracking process, there will be many similar objects, and it is easy to track the wrong object due to the weak discriminative ability of the network. At the same time, the classification and regression of SiamRPN ++ are usually optimized independently, which will cause a mismatch problem, that is, the location with the highest classification confidence is not necessarily the object. To address these problems, we proposed a Siamese network tracker by attention module and relation detector module (SiamAR). First, we introduce a multi-scale attention mechanism in SiamRPN++ to capture information at different scales, and fuse spatial attention and channel attention to improving the ability to learn feature information. Not only different receptive fields are obtained, but also useful features are selectively focused and less useful features are suppressed. In order not to affect the computational efficiency, the method of grouping parallel computing is used. Secondly, we add a relation detector module to our tracker to filter out distractors from the background and distinguish the object in the cluttered background. Experiment results show that our algorithm out-performs several well-known tracking algorithms in terms of tracking accuracy and robustness.
{"title":"Siamese Network Tracker by Attention Module and Relation Detector Module","authors":"Xiaohan Liu, Aimin Li, Deqi Liu, Dexu Yao, Mengfan Cheng","doi":"10.1109/IJCNN55064.2022.9892067","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892067","url":null,"abstract":"In recent years, object tracking techniques based on Siamese networks have shown excellent tracking performance. However, in the tracking process, there will be many similar objects, and it is easy to track the wrong object due to the weak discriminative ability of the network. At the same time, the classification and regression of SiamRPN ++ are usually optimized independently, which will cause a mismatch problem, that is, the location with the highest classification confidence is not necessarily the object. To address these problems, we proposed a Siamese network tracker by attention module and relation detector module (SiamAR). First, we introduce a multi-scale attention mechanism in SiamRPN++ to capture information at different scales, and fuse spatial attention and channel attention to improving the ability to learn feature information. Not only different receptive fields are obtained, but also useful features are selectively focused and less useful features are suppressed. In order not to affect the computational efficiency, the method of grouping parallel computing is used. Secondly, we add a relation detector module to our tracker to filter out distractors from the background and distinguish the object in the cluttered background. Experiment results show that our algorithm out-performs several well-known tracking algorithms in terms of tracking accuracy and robustness.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127886975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9889789
Yancheng Li, Qingzhong Ai, Fumihiko Ino
Recently, tile pruning has been widely studied to accelerate the inference of deep neural networks (DNNs). However, we found that the loss due to tile pruning, which can eliminate important elements together with unimportant elements, is large on trained DNNs. In this study, we propose a one-shot reparameterization method, called TileTrans, to reduce the loss of tile pruning. Specifically, we repermute the rows or columns of the weight matrix such that the model architecture can be kept unchanged after reparameterization. This repermutation realizes the reparameterization of the DNN model without any retraining. The proposed reparameterization method combines important elements into the same tile; thus, preserving the important elements after the tile pruning. Furthermore, TileTrans can be seamlessly integrated into existing tile pruning methods because it is a pre-processing method executed before pruning, which is orthogonal to most existing methods. The experimental results demonstrate that our method is essential in reducing the loss of tile pruning on DNNs. Specifically, the accuracy is improved by up to 17% for AlexNet while 5% for ResNet-34, where both models are pre-trained on ImageNet.
{"title":"A One-Shot Reparameterization Method for Reducing the Loss of Tile Pruning on DNNs","authors":"Yancheng Li, Qingzhong Ai, Fumihiko Ino","doi":"10.1109/IJCNN55064.2022.9889789","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9889789","url":null,"abstract":"Recently, tile pruning has been widely studied to accelerate the inference of deep neural networks (DNNs). However, we found that the loss due to tile pruning, which can eliminate important elements together with unimportant elements, is large on trained DNNs. In this study, we propose a one-shot reparameterization method, called TileTrans, to reduce the loss of tile pruning. Specifically, we repermute the rows or columns of the weight matrix such that the model architecture can be kept unchanged after reparameterization. This repermutation realizes the reparameterization of the DNN model without any retraining. The proposed reparameterization method combines important elements into the same tile; thus, preserving the important elements after the tile pruning. Furthermore, TileTrans can be seamlessly integrated into existing tile pruning methods because it is a pre-processing method executed before pruning, which is orthogonal to most existing methods. The experimental results demonstrate that our method is essential in reducing the loss of tile pruning on DNNs. Specifically, the accuracy is improved by up to 17% for AlexNet while 5% for ResNet-34, where both models are pre-trained on ImageNet.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126544379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892751
Kengo Machida, K. Uto, K. Shinoda, Taiji Suzuki
In neural architecture search (NAS), differentiable architecture search (DARTS) has recently attracted much attention due to its high efficiency. However, this method finds a model with the weights converging faster than the others, and such a model with fastest convergence often leads to overfitting. Accordingly, the resulting model cannot always be well-generalized. To overcome this problem, we propose a method called minimum stable rank DARTS (MSR-DARTS), for finding a model with the best generalization error by replacing architecture optimization with the selection process using the minimum stable rank criterion. Specifically, a convolution operator is represented by a matrix, and MSR-DARTS selects the one with the smallest stable rank. We evaluated MSR-DARTS on CIFAR-10 and ImageNet datasets. It achieves an error rate of 2.54% with 4.0M parameters within 0.3 GPU-days on CIFAR-10, and a top-1 error rate of 23.9% on ImageNet.
{"title":"MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search","authors":"Kengo Machida, K. Uto, K. Shinoda, Taiji Suzuki","doi":"10.1109/IJCNN55064.2022.9892751","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892751","url":null,"abstract":"In neural architecture search (NAS), differentiable architecture search (DARTS) has recently attracted much attention due to its high efficiency. However, this method finds a model with the weights converging faster than the others, and such a model with fastest convergence often leads to overfitting. Accordingly, the resulting model cannot always be well-generalized. To overcome this problem, we propose a method called minimum stable rank DARTS (MSR-DARTS), for finding a model with the best generalization error by replacing architecture optimization with the selection process using the minimum stable rank criterion. Specifically, a convolution operator is represented by a matrix, and MSR-DARTS selects the one with the smallest stable rank. We evaluated MSR-DARTS on CIFAR-10 and ImageNet datasets. It achieves an error rate of 2.54% with 4.0M parameters within 0.3 GPU-days on CIFAR-10, and a top-1 error rate of 23.9% on ImageNet.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"33 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125712295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892886
Chao Wei, Zhidong Deng
Few-shot graph-level classification based on graph neural networks is critical in many tasks including drug and material discovery. We present a novel graph contrastive relation network (GCRNet) by introducing a practical yet straightforward graph meta-baseline with contrastive loss to gain robust representation and meta-classifier to realize more suitable similarity metric, which is more adaptive for graph few-shot problems. Experimental results demonstrate that the proposed method achieves 8%-12% in 5-shot, 5%-8% in 10 shot, and 1%-5% in 20-shot improvements, respectively, compared to the existing state-of-the-art methods.
{"title":"Few-shot Graph Classification with Contrastive Loss and Meta-classifier","authors":"Chao Wei, Zhidong Deng","doi":"10.1109/IJCNN55064.2022.9892886","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892886","url":null,"abstract":"Few-shot graph-level classification based on graph neural networks is critical in many tasks including drug and material discovery. We present a novel graph contrastive relation network (GCRNet) by introducing a practical yet straightforward graph meta-baseline with contrastive loss to gain robust representation and meta-classifier to realize more suitable similarity metric, which is more adaptive for graph few-shot problems. Experimental results demonstrate that the proposed method achieves 8%-12% in 5-shot, 5%-8% in 10 shot, and 1%-5% in 20-shot improvements, respectively, compared to the existing state-of-the-art methods.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121980984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892307
He Zhang, Hanling Zhang
Micro-expression has the characteristics of spontaneity, low intensity, and short duration, which reflects a real personal emotion. Therefore, micro-expression recognition (MER) has been applied widely in lie detection, depression analysis, human-computer interaction systems, and commercial negotiation. Micro-expressions usually occur when people attempt to cover up their true feelings, especially in high-stake environments. In the early stage, the study of micro-expressions was mainly from a psychological point of view and required a very specialized skill. MER based on deep learning is a hot research direction recently, which generally includes several stages, such as image preprocessing, feature extraction, and emotion classification. In this paper, we first introduce the problems and challenges MER encountered. Then we present the commonly used micro-expression datasets and methods of image preprocessing. Next, we describe the MER methods based on deep learning in recent years and classify them according to the network structure. Afterward, we present the evaluation metrics and protocol and compare different algorithms on the composite dataset. Finally, we conclude and provide a prospect of the future work of MER.
{"title":"A Review of Micro-expression Recognition based on Deep Learning","authors":"He Zhang, Hanling Zhang","doi":"10.1109/IJCNN55064.2022.9892307","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892307","url":null,"abstract":"Micro-expression has the characteristics of spontaneity, low intensity, and short duration, which reflects a real personal emotion. Therefore, micro-expression recognition (MER) has been applied widely in lie detection, depression analysis, human-computer interaction systems, and commercial negotiation. Micro-expressions usually occur when people attempt to cover up their true feelings, especially in high-stake environments. In the early stage, the study of micro-expressions was mainly from a psychological point of view and required a very specialized skill. MER based on deep learning is a hot research direction recently, which generally includes several stages, such as image preprocessing, feature extraction, and emotion classification. In this paper, we first introduce the problems and challenges MER encountered. Then we present the commonly used micro-expression datasets and methods of image preprocessing. Next, we describe the MER methods based on deep learning in recent years and classify them according to the network structure. Afterward, we present the evaluation metrics and protocol and compare different algorithms on the composite dataset. Finally, we conclude and provide a prospect of the future work of MER.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122246936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892276
Kai Chen, Yongqiang Ma, Mingyang Sheng, N. Zheng
The reconstruction of visual stimulus images from functional Magnetic Resonance Imaging (fMRI) has received extensive attention in recent years, which provides a possibility to interpret the human brain. Due to the high-dimensional and high-noise characteristics of fMRI data, how to extract stable, reliable and useful information from fMRI data for image reconstruction has become a challenging problem. Inspired by the mechanism of human visual attention, in this paper, we propose a novel method of reconstructing visual stimulus images, which first decodes human visual salient region from fMRI, we define human visual salient region as foreground attention (F-attention), and then reconstructs the visual images guided by F-attention. Because the human brain is strongly wound into sulci and gyri, some spatially adjacent voxels are not connected in practice. Therefore, it is necessary to consider the global information when decoding fMRI, so we introduce the self-attention module for capturing global information into the process of decoding F-attention. In addition, in order to obtain more loss constraints in the training process of encoder-decoder, we also propose a new training strategy called Loop-Enc-Dec. The experimental results show that the F-attention decoder decodes the visual attention from fMRI successfully, and the Loop-Enc-Dec guided by F-attention can also well reconstruct the visual stimulus images.
{"title":"Foreground-attention in neural decoding: Guiding Loop-Enc-Dec to reconstruct visual stimulus images from fMRI","authors":"Kai Chen, Yongqiang Ma, Mingyang Sheng, N. Zheng","doi":"10.1109/IJCNN55064.2022.9892276","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892276","url":null,"abstract":"The reconstruction of visual stimulus images from functional Magnetic Resonance Imaging (fMRI) has received extensive attention in recent years, which provides a possibility to interpret the human brain. Due to the high-dimensional and high-noise characteristics of fMRI data, how to extract stable, reliable and useful information from fMRI data for image reconstruction has become a challenging problem. Inspired by the mechanism of human visual attention, in this paper, we propose a novel method of reconstructing visual stimulus images, which first decodes human visual salient region from fMRI, we define human visual salient region as foreground attention (F-attention), and then reconstructs the visual images guided by F-attention. Because the human brain is strongly wound into sulci and gyri, some spatially adjacent voxels are not connected in practice. Therefore, it is necessary to consider the global information when decoding fMRI, so we introduce the self-attention module for capturing global information into the process of decoding F-attention. In addition, in order to obtain more loss constraints in the training process of encoder-decoder, we also propose a new training strategy called Loop-Enc-Dec. The experimental results show that the F-attention decoder decodes the visual attention from fMRI successfully, and the Loop-Enc-Dec guided by F-attention can also well reconstruct the visual stimulus images.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115796356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892439
Di Zhao, Yun Sing Koh, Philippe Fournier-Viger
Streaming data has become more common as our ability to collect data in real-time increases. A primary concern in dealing with data streams is concept drift, which describes changes in the underlying distribution of streaming data. Measuring drift severity is crucial for model adaptation. Drift severity can be a proxy in choosing concept drift adaptation strategies. Current methods measure drift severity by monitoring the changes in the learner performance or measuring the difference between data distributions. However, these methods cannot measure the drift severity if the ground truth labels are unavailable. Specifically, performance-based methods cannot measure marginal drift, and distribution-based methods cannot measure conditional drift. We propose a novel framework named Tree-based Drift Measurement (TDM) that measures both marginal and conditional drift without revisiting historical data. TDM measures the difference between tree classifiers by transforming them into sets of binary vectors. An experiment shows that TDM achieves similar performance to the state-of-the-art methods and provides the best trade-off between runtime and memory usage. A case study shows that the online learner performance can be improved by adapting different drift adaptation strategies based on the drift severity.
{"title":"Measuring Drift Severity by Tree Structure Classifiers","authors":"Di Zhao, Yun Sing Koh, Philippe Fournier-Viger","doi":"10.1109/IJCNN55064.2022.9892439","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892439","url":null,"abstract":"Streaming data has become more common as our ability to collect data in real-time increases. A primary concern in dealing with data streams is concept drift, which describes changes in the underlying distribution of streaming data. Measuring drift severity is crucial for model adaptation. Drift severity can be a proxy in choosing concept drift adaptation strategies. Current methods measure drift severity by monitoring the changes in the learner performance or measuring the difference between data distributions. However, these methods cannot measure the drift severity if the ground truth labels are unavailable. Specifically, performance-based methods cannot measure marginal drift, and distribution-based methods cannot measure conditional drift. We propose a novel framework named Tree-based Drift Measurement (TDM) that measures both marginal and conditional drift without revisiting historical data. TDM measures the difference between tree classifiers by transforming them into sets of binary vectors. An experiment shows that TDM achieves similar performance to the state-of-the-art methods and provides the best trade-off between runtime and memory usage. A case study shows that the online learner performance can be improved by adapting different drift adaptation strategies based on the drift severity.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131348774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-18DOI: 10.1109/IJCNN55064.2022.9892001
A. Wawrzynczak, M. Berendt-Marchel
The neural networks are powerful as nonlinear signal processors. This paper deals with the problem of employing the feedforward neural networks (FFNNs) to simulate the time-dependent distribution of the airborne toxin in the urbanized area. The spatial distribution of the contaminant is the multidimensional function dependent on the weather conditions (wind direction and speed), coordinates of the contamination sources, the release rate, and its duration. In this paper, we try to answer what topology should be the multilayered FFNN to forecast the contaminant strength correctly at the given point of the urbanized area at a given time. The comparison between the FFNNs is made based on the standard performance measures like correlation R and mean square error (MSE). Additionally, the new measure estimating the quality of the neural networks forecasts in subsequent time intervals after the release is proposed. In combination with R and MSE, the proposed measure allows identifying the well-trained network unambiguously. Such a neural network may enable creating an emergency system localizing the contaminant source in an urban area in real-time. However, in such a system time of answer depends directly on the multiple times run dispersion model computational time. This time is expected in minutes for custom dispersion models in urban areas and can be shortened to seconds in the case of artificial neural networks.
{"title":"Feedforward neural networks in forecasting the spatial distribution of the time-dependent multidimensional functions","authors":"A. Wawrzynczak, M. Berendt-Marchel","doi":"10.1109/IJCNN55064.2022.9892001","DOIUrl":"https://doi.org/10.1109/IJCNN55064.2022.9892001","url":null,"abstract":"The neural networks are powerful as nonlinear signal processors. This paper deals with the problem of employing the feedforward neural networks (FFNNs) to simulate the time-dependent distribution of the airborne toxin in the urbanized area. The spatial distribution of the contaminant is the multidimensional function dependent on the weather conditions (wind direction and speed), coordinates of the contamination sources, the release rate, and its duration. In this paper, we try to answer what topology should be the multilayered FFNN to forecast the contaminant strength correctly at the given point of the urbanized area at a given time. The comparison between the FFNNs is made based on the standard performance measures like correlation R and mean square error (MSE). Additionally, the new measure estimating the quality of the neural networks forecasts in subsequent time intervals after the release is proposed. In combination with R and MSE, the proposed measure allows identifying the well-trained network unambiguously. Such a neural network may enable creating an emergency system localizing the contaminant source in an urban area in real-time. However, in such a system time of answer depends directly on the multiple times run dispersion model computational time. This time is expected in minutes for custom dispersion models in urban areas and can be shortened to seconds in the case of artificial neural networks.","PeriodicalId":106974,"journal":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131456451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：