The development of new electric traction machines is a time-consuming process as it involves intensive testing on motor test benches. Machine-Learning-empowered monitoring offers the opportunity to anticipate costly f...
详细信息
ISBN:
(纸本)9781665473309
The development of new electric traction machines is a time-consuming process as it involves intensive testing on motor test benches. Machine-Learning-empowered monitoring offers the opportunity to anticipate costly failures early and hence reduce development time. However, machine learning (ML) for process monitoring requires large amounts of training data, especially as the targeted fault states are scarce and yet diverse in their appearances. Therefore, we propose to use synthetic time series data to leverage the high cost of acquiring training data from experiments in real test benches. In this article, we present a novel scheme to generate synthetic data based on a sub-dimensional time series representation. We introduce a highly flexible model by mapping the data to a latent representation and approximating the latent data distribution by a Gaussian Mixture Model. In addition, we propose the Fr ' echet InceptionTime Distance (FITD) as a new distance measure to evaluate the generated data. It allows extracting characteristics at different scales by using multiple kernel sizes. In this way, we ensure that the synthesized data contains characteristics similar to those present in the real data. In our experiment, we train two types of fault detectors, one based on real data of a motor test bench and the other based on synthetic data. We also consider employing fault-aware conditional architectures to generate training data for different fault types explicitly. Our final results show that using synthesized data in the training process increases the performance in terms of classification accuracy score (CAS) up to 29%.
This work describes our third-place solution in both the core and transfer learning challenges of Weather4cast - IEEE BigData Cup. The solution builds on our success in Weather4cast - Stage 1 [1], and uses the same Va...
详细信息
ISBN:
(纸本)9781665439022
This work describes our third-place solution in both the core and transfer learning challenges of Weather4cast - IEEE BigData Cup. The solution builds on our success in Weather4cast - Stage 1 [1], and uses the same variational U-Net architecture. Building on the lessons learned from Weather4cast - Stage 1, we enhanced the model's performance through the use of data augmentations and model blending. Furthermore, we explored transfer learning between the two competitions. The code for this solution is available at https://***/qiq208/w4c-2021IEEE
In this paper, we explore the use of a factorized hierarchical variational autoencoder (FHVAE) model to learn an unsupervised latent representation for dialect identification (DID). An FHVAE can learn a latent space t...
详细信息
ISBN:
(纸本)9781538643341
In this paper, we explore the use of a factorized hierarchical variational autoencoder (FHVAE) model to learn an unsupervised latent representation for dialect identification (DID). An FHVAE can learn a latent space that separates the more static attributes within an utterance from the more dynamic attributes by encoding them into two different sets of latent variables. Useful factors for dialect identification, such as phonetic or linguistic content, are encoded by a segmental latent variable, while irrelevant factors that are relatively constant within a sequence, such as a channel or a speaker information, are encoded by a sequential latent variable. The disentanglement property makes the segmental latent variable less susceptible to channel and speaker variation, and thus reduces degradation from channel domain mismatch. We demonstrate that on fully-supervised DID tasks, an end-to-end model trained on the features extracted from the FHVAE model achieves the best performance, compared to the same model trained on conventional acoustic features and an i-vector based system. Moreover, we also show that the proposed approach can leverage a large amount of unlabeled data for FHVAE training to learn domain-invariant features for DID, and significantly improve the performance in a low-resource condition, where the labels for the in-domain data are not available.
Deep learning approaches have been used extensively for medical image segmentation tasks. Training deep networks for segmentation, however, typically requires manually delineated examples which provide a ground truth ...
详细信息
ISBN:
(纸本)9781510633940
Deep learning approaches have been used extensively for medical image segmentation tasks. Training deep networks for segmentation, however, typically requires manually delineated examples which provide a ground truth for optimization of the network. In this work, we present a neural network architecture that segments vascular structures in retinal OCTA images without the need of direct supervision. Instead, we propose a variational intensity cross channel encoder that finds vessel masks by exploiting the common underlying structure shared by two OCTA images of the the same region but acquired on different devices. Experimental results demonstrate significant improvement over three existing methods that are commonly used.
In multi-turn dialogue generation, it's still a challenge to generate coherent responses given dialogue history, which requires neural models to learn complex semantic structures between responses and contexts. It...
详细信息
In most practical adaptive filtering problems, estimated filters are not arbitrary, but instead lie on a manifold that encapsulates characteristics of the problem at hand. Consequently, it is desirable to steer adapta...
详细信息
With the rise of cloud computing, many applications have been implemented into microservices to fully utilize cloud computing for scalability and maintainability purposes. However, there are some traditional monolith ...
详细信息
ISBN:
(数字)9781665475341
ISBN:
(纸本)9781665475341
With the rise of cloud computing, many applications have been implemented into microservices to fully utilize cloud computing for scalability and maintainability purposes. However, there are some traditional monolith applications that developers would like to partition into microservices. Unfortunately, it is difficult to find a solution when considering multiple factors (i.e., the strong dependency in each cluster and how often different microservices communicate with each other). Further, because we allow duplications of classes in multiple microservices to reduce the communications between them, the number of duplicated classes is also another important factor for maintainability. Therefore, we need to use machine learning algorithms to approximate a good solution due to the infeasibility of finding the optimal solution. We apply the variational autoencoder to extract features of classes and use the fuzzy c means to group the classes into microservices according to their extracted features. As a result, our approach outperforms the other baselines in some significant metrics. Also, when we allow duplication, we find that it is helpful in terms of reducing the overhead of communications between microservices.
This article presents the process of building a system generating music content of a specified emotion. As the emotion labels, four basic emotions: happy, angry, sad, relaxed, which correspond to the four quarters of ...
详细信息
ISBN:
(纸本)9781665442077
This article presents the process of building a system generating music content of a specified emotion. As the emotion labels, four basic emotions: happy, angry, sad, relaxed, which correspond to the four quarters of Russell's model, were used. Conditional variational autoencoder using a recurrent neural network for sequence processing was used as a generative model. The obtained results in the form of the generated music examples with a specific emotion are convincing in their structure and sound. The generated examples were evaluated through comparison with the training set.
Recently, adversarial examples become one of the most dangerous risks in deep learning, which affects applications of real world such as robotics, cyber-security and computer vision. In image classification, adversari...
详细信息
ISBN:
(纸本)9781510640412
Recently, adversarial examples become one of the most dangerous risks in deep learning, which affects applications of real world such as robotics, cyber-security and computer vision. In image classification, adversarial attacks showed the ability to fool classifiers with small imperceptible perturbations added to the input. In this paper, we present an efficient defense mechanism, we call DVAE-SR that combine variational autoencoder and super-resolution to eliminate adversarial perturbation from image input before feeding it to the CNN classifier. The DVAE-SR can successfully defend against both white-box and black-box attacks without retraining CNN classifier and it recovers better accuracy than Defense-GAN and Defense-VAE..
Type Design is a domain that multiple times has profited from the emergence of new tools and technologies. The transformation of type from physical to digital, the dissemination of font design software and the adoptio...
详细信息
ISBN:
(纸本)9783031299551;9783031299568
Type Design is a domain that multiple times has profited from the emergence of new tools and technologies. The transformation of type from physical to digital, the dissemination of font design software and the adoption of web typography make type design better known and more accessible. This domain has received an even greater push with the increasing adoption of generative tools to create more diverse and experimental fonts. Nowadays, with the application of Machine Learning to various domains, typography has also been influenced by it. In this work, we produce a dataset by extracting letter skeletons from a collection of existing fonts. Then we trained a variational autoencoder and a Sketch Decoder to learn to create these skeletons that can be used to generate new ones by exploring the latent space. This process also allows us to control the style of the resulting skeletons and interpolate between different characters. Finally, we developed new glyphs by filling the generated skeletons based on the original letters' stroke width and showing some applications of the results.
暂无评论