检索结果-内蒙古大学图书馆

PCGen: A Fully Parallelizable Point Cloud Generative Model

SENSORS 2024年第5期24卷 1414页

作者： Vercheval, Nicolas Royen, Remco Munteanu, Adrian Pizurica, Aleksandra Univ Ghent Fac Engn & Architecture Dept Telecommun & Informat Proc Res Grp Artificial Intelligence & Sparse Modelling B-9000 Ghent Belgium Univ Ghent Fac Engn & Architecture Dept Elect & Informat Syst Clifford Res Grp B-9000 Ghent Belgium Vrije Univ Brussel Dept Elect & Informat ETRO Fac Engn B-1050 Brussels Belgium

Generative models have the potential to revolutionize 3D extended reality. A primary obstacle is that augmented and virtual reality need real-time computing. Current state-of-the-art point cloud random generation methods are not fast enough for these applications. We introduce a vector-quantized variational autoencoder model (VQVAE) that can synthesize high-quality point clouds in milliseconds. Unlike previous work in VQVAEs, our model offers a compact sample representation suitable for conditional generation and data exploration with potential applications in rapid prototyping. We achieve this result by combining architectural improvements with an innovative approach for probabilistic random generation. First, we rethink current parallel point cloud autoencoder structures, and we propose several solutions to improve robustness, efficiency and reconstruction quality. Notable contributions in the decoder architecture include an innovative computation layer to process the shape semantic information, an attention mechanism that helps the model focus on different areas and a filter to cover possible sampling errors. Secondly, we introduce a parallel sampling strategy for VQVAE models consisting of a double encoding system, where a variational autoencoder learns how to generate the complex discrete distribution of the VQVAE, not only allowing quick inference but also describing the shape with a few global variables. We compare the proposed decoder and our VQVAE model with established and concurrent work, and we prove, one by one, the validity of the single contributions.

关键词： point clouds autoencoder variational autoencoder vector-quantized variational autoencoder real-time computing

来源：评论

学校读者我要写书评

暂无评论

Disentangling the correlated continuous and discrete generative factors of data

引用

PATTERN RECOGNITION 2023年 133卷

作者： Choi, Jaewoong Hwang, Geonho Kang, Myungjoo Seoul Natl Univ Dept Math Sci 1 Gwanak Ro Seoul 08826 South Korea Korea Inst Adv Study KIAS Ctr Artificial Intelligence & Nat Sci Seoul South Korea

Real-world data typically include discrete generative factors, such as category labels and the existence of objects, as well as continuous generative factors. Continuous generative factors may be dependent on or independent of discrete generative factors. For instance, an intra-class variation of a category is dependent on the discrete generative factor, whereas a common variation of all categories is not. Most previous attempts to integrate discrete generative factors into disentanglement assumed statistical independence between the continuous and discrete variables. In this paper, we propose a variational autoencoder(VAE) model capable of disentangling both continuous generative factors. To represent these generative factors, we introduce two sets of continuous latent variables: a private variable and a public variable . The private and public variables represent the intra-class variations and common variations in categories, respectively. Our proposed framework models the private variable as a Gaussian mixture and the public variable as a Gaussian. Each mode of the private variable is responsible for a class of discrete variables. Our proposed model, called Discond-VAE, DISentangles the class-dependent CONtinuous factors from the Discrete factors by introducing private variables. The experiments showed that Discond-VAE could discover private and public factors from the data. Moreover, even under the dataset with only public factors, Discond-VAE does not fail and adapts private variables to represent public factors.(c) 2022 Elsevier Ltd. All rights reserved.

关键词： variational autoencoder Disentanglement Generative model Representation learning

来源：评论

学校读者我要写书评

暂无评论

An Auto-Encoder with Genetic Algorithm for High Dimensional Data: Towards Accurate and Interpretable Outlier Detection

引用

ALGORITHMS 2022年第11期15卷 429-429页

作者： Li, Jiamu Zhang, Ji Bah, Mohamed Jaward Wang, Jian Zhu, Youwen Yang, Gaoming Li, Lingling Zhang, Kexin Nanjing Univ Aeronaut & Astronaut Sch Comp Sci & Technol Nanjing 210016 Peoples R China Univ Southern Queensland Sch Math Phys & Comp Toowoomba Qld 4350 Australia Zhejiang Lab Big Data Intelligence Res Ctr Hangzhou 311121 Peoples R China Anhui Univ Sci & Technol Sch Comp Sci & Engn Huainan 243002 Peoples R China Zhengzhou Univ Aeronaut Sch Intelligent Engn Zhengzhou 450046 Peoples R China

When dealing with high-dimensional data, such as in biometric, e-commerce, or industrial applications, it is extremely hard to capture the abnormalities in full space due to the curse of dimensionality. Furthermore, it is becoming increasingly complicated but essential to provide interpretations for outlier detection results in high-dimensional space as a consequence of the large number of features. To alleviate these issues, we propose a new model based on a variational autoencoder and Genetic Algorithm (VAEGA) for detecting outliers in subspaces of high-dimensional data. The proposed model employs a neural network to create a probabilistic dimensionality reduction variational autoencoder (VAE) that applies its low-dimensional hidden space to characterize the high-dimensional inputs. Then, the hidden vector is sampled randomly from the hidden space to reconstruct the data so that it closely matches the input data. The reconstruction error is then computed to determine an outlier score, and samples exceeding the threshold are tentatively identified as outliers. In the second step, a genetic algorithm (GA) is used as a basis for examining and analyzing the abnormal subspace of the outlier set obtained by the VAE layer. After encoding the outlier dataset's subspaces, the degree of anomaly for the detected subspaces is calculated using the redefined fitness function. Finally, the abnormal subspace is calculated for the detected point by selecting the subspace with the highest degree of anomaly. The clustering of abnormal subspaces helps filter outliers that are mislabeled (false positives), and the VAE layer adjusts the network weights based on the false positives. When compared to other methods using five public datasets, the VAEGA outlier detection model results are highly interpretable and outperform or have competitive performance compared to current contemporary methods.

关键词： outlier detection variational autoencoder genetic algorithm abnormal subspace

来源：评论

学校读者我要写书评

暂无评论

Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence

引用

FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY 2024年 12卷 1350135页

作者： Dindorf, Carlo Dully, Jonas Konradi, Juergen Wolf, Claudia Becker, Stephan Simon, Steven Huthwelker, Janine Werthmann, Frederike Kniepert, Johanna Drees, Philipp Betz, Ulrich Froehlich, Michael Univ Kaiserslautern Landau Dept Sports Sci Kaiserslautern Germany Johannes Gutenberg Univ Mainz Univ Med Ctr Inst Phys Therapy Prevent & Rehabil Mainz Germany Johannes Gutenberg Univ Mainz Univ Med Ctr Dept Orthoped & Trauma Surg Mainz Germany

Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture ***: Data were collected from 338 subjects through surface topography. A variational autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature ***: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data ***: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain.

关键词： machine learning deep learning spine variational autoencoder data augmentation statistical parametric mapping

来源：评论

学校读者我要写书评

暂无评论

3D Generative Model Latent Disentanglement via Local Eigenprojection

引用

COMPUTER GRAPHICS FORUM 2023年第6期42卷 e14793-e14793页

作者： Foti, Simone Koo, Bongjin Stoyanov, Danail Clarkson, Matthew J. UCL London England Univ Calif Santa Barbara Santa Barbara CA USA

Designing realistic digital humans is extremely complex. Most data-driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper, we overcome this limitation by introducing a novel loss function grounded in spectral geometry and applicable to different neural-network-based generative models of 3D head and body meshes. Encouraging the latent variables of mesh variational autoencoders (VAEs) or generative adversarial networks (GANs) to follow the local eigenprojections of identity attributes, we improve latent disentanglement and properly decouple the attribute creation. Experimental results show that our local eigenprojection disentangled (LED) models not only offer improved disentanglement with respect to the state-of-the-art, but also maintain good generation capabilities with training times comparable to the vanilla implementations of the models. Our code and pre-trained models are available at .

关键词： disentanglement generative adversarial networks geometric deep learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Human Laughter Generation using Hybrid Generative Models

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2021年第5期15卷 1590-1609页

作者： Mansouri, Nadia Lachiri, Zied El Manar Univ Natl Engn Sch Tunisia Tunis 1002 Tunisia

Laughter is one of the most important nonverbal sound that human generates. It is a means for expressing his emotions. The acoustic and contextual features of this specific sound are different from those of speech and many difficulties arise during their modeling process. During this work, we propose an audio laughter generation system based on unsupervised generative models: the autoencoder (AE) and its variants. This procedure is the association of three main sub-process, (1) the analysis which consist of extracting the log magnitude spectrogram from the laughter database, (2) the generative models training, (3) the synthesis stage which incorporate the involvement of an intermediate mechanism: the vocoder. To improve the synthesis quality, we suggest two hybrid models (LSTM-VAE, GRU-VAE and CNN-VAE) that combine the representation learning capacity of variational autoencoder (VAE) with the temporal modelling ability of a long short-term memory RNN (LSTM) and the CNN ability to learn invariant features. To figure out the performance of our proposed audio laughter generation process, objective evaluation (RMSE) and a perceptual audio quality test (listening test) were conducted. According to these evaluation metrics, we can show that the GRU-VAE outperforms the other VAE models.

关键词： Laughter Synthesis variational autoencoder autoencoder Objective and Subjective Evaluation

来源：评论

学校读者我要写书评

暂无评论

Class-Incremental Learning With Deep Generative Feature Replay for DNA Methylation-Based Cancer Classification

引用

IEEE ACCESS 2020年 8卷 210800-210815页

作者： Batbaatar, Erdenebileg Park, Kwang Ho Amarbayasgalan, Tsatsral Davagdorj, Khishigsuren Munkhdalai, Lkhagvadorj Pham, Van-Huy Ryu, Keun Ho Chungbuk Natl Univ Sch Elect & Comp Engn Database Bioinformat Lab Cheongju 28644 South Korea Ton Duc Thang Univ Fac Informat Technol Ho Chi Minh City 700000 Vietnam

Developing lifelong learning algorithms are mandatory for computational systems biology. Recently, many studies have shown how to extract biologically relevant information from high-dimensional data to understand the complexity of cancer by taking the benefit of deep learning (DL). Unfortunately, new cancer growing up into the hundred types that make systems difficult to classify them efficiently. In contrast, the current state-of-the-art continual learning (CL) methods are not designed for the dynamic characteristics of high-dimensional data. And data security and privacy are some of the main issues in the biomedical field. This article addresses three practical challenges for class-incremental learning (Class-IL) such as data privacy, high-dimensionality, and incremental learning problems. To solve this, we propose a novel continual learning approach, called Deep Generative Feature Replay (DGFR), for cancer classification tasks. DGFR consists of an incremental feature selection (IFS) and a scholar network (SN). IFS is used for selecting the most significant CpG sites from high-dimensional data. We investigate different dimensions to find an optimal number of selected CpG sites. SN employs a deep generative model for generating pseudo data without accessing past samples and a neural network classifier for predicting cancer types. We use a variational autoencoder (VAE), which has been successfully applied to this research field in previous works. All networks are sequentially trained on multiple tasks in the Class-IL setting. We evaluated the proposed method on the publicly available DNA methylation data. The experimental results show that the proposed DGFR achieves a significantly superior quality of cancer classification tasks with various state-of-the-art methods in terms of accuracy.

关键词： Cancer DNA Task analysis Data models Computational modeling Feature extraction Biological system modeling Computational biology deep learning class-incremental learning continual learning deep generative model variational autoencoder DNA methylation cancer classification

来源：评论

学校读者我要写书评

暂无评论

Multicategory choice modeling with sparse and high dimensional data: A Bayesian deep learning approach

引用

DECISION SUPPORT SYSTEMS 2022年 157卷 113766-113766页

作者： Xia, Feihong Chatterjee, Rabikar Univ Rhode Isl Coll Business 233 Ballentine Hall7 Lippitt Rd Kingston RI 02881 USA Univ Pittsburgh Joseph M Katz Grad Sch Business 276C Mervis Hall Pittsburgh PA 15260 USA

The availability of sparse and high dimensional consumer shopping data poses a challenge for researchers for accurate and efficient analysis. While deep learning models can handle such data, most of the results from these models are uninterpretable. This greatly limits their value in applications aimed at better understanding multicategory shopping behavior and assisting managerial decision-making. Thus, a new approach is needed to analyze high dimensional consumer shopping data in an efficient and interpretable manner, with the potential to greatly strengthen decision support systems for managers especially at large consumer packaged goods firms and giant retailers. We propose a Bayesian deep learning approach based on variational autoencoder (VAE) designed to efficiently capture often complex and multifaceted interrelationships across items in the shopping baskets, in the form of substitute and complementary cross effects (which are observable and controllable) and coincidences (which are not). The benefits of the proposed approach are empirically demonstrated by applying our model to a high dimensional supermarket shopping dataset covering very large numbers of products at the stock-keeping unit (SKU) level, households, and shopping trips. We discuss implications for managerial decision-making and identify promising research directions.

关键词： Consumer shopping basket Consumer multicategory choice modeling Sparsity High dimensional data variational autoencoder Bayesian deep learning

来源：评论

学校读者我要写书评

暂无评论

ELVISort: encoding latent variables for instant sorting, an artificial intelligence-based end-to-end solution

引用

JOURNAL OF NEURAL ENGINEERING 2021年第4期18卷

作者： Rokai, Janos Racz, Melinda Fiath, Richard Ulbert, Istvan Marton, Gergely Res Ctr Nat Sci Inst Cognit Neurosci & Psychol Magyar Tudosok Korutja 2 H-1117 Budapest Hungary Semmelweis Univ Sch PhD Studies Ulloi Ut 26 H-1085 Budapest Hungary Pazmany Peter Catholic Univ Fac Informat Technol & Bion Prater Utca 50-A H-1083 Budapest Hungary

Objective. The growing number of recording sites of silicon-based probes means that an increasing amount of neural cell activities can be recorded simultaneously, facilitating the investigation of underlying complex neural dynamics. In order to overcome the challenges generated by the increasing number of channels, highly automated signal processing tools are needed. Our goal was to build a spike sorting model that can perform as well as offline solutions while maintaining high efficiency, enabling high-performance online sorting. Approach. In this paper we present ELVISort, a deep learning method that combines the detection and clustering of different action potentials in an end-to-end fashion. Main results. The performance of ELVISort is comparable with other spike sorting methods that use manual or semi-manual techniques, while exceeding the methods which use an automatic approach: ELVISort has been tested on three independent datasets and yielded average F-1 scores of 0.96, 0.82 and 0.81, which comparable with the results of state-of-the-art algorithms on the same data. We show that despite the good performance, ELVISort is capable to process data in real-time: the time it needs to execute the necessary computations for a sample of given length is only 1/15.71 of its actual duration (i.e. the sampling time multiplied by the number of the sampling points). Significance. ELVISort, because of its end-to-end nature, can exploit the massively parallel processing capabilities of GPUs via deep learning frameworks by processing multiple batches in parallel, with the potential to be used on other cutting-edge AI-specific hardware such as TPUs, enabling the development of integrated, portable and real-time spike sorting systems with similar performance to offline sorters.

关键词： spike sorting deep learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multi source deep learning method for drug-protein interaction prediction using k-mers and chaos game representation

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2024年 246卷

作者： Mesrabadi, Hengame Abbasi Faez, Karim Pirgazi, Jamshid Islamic Azad Univ Fac Comp & Informat Technol Engn Qazvin Branch Qazvin Iran Amirkabir Univ Technol Tehran Polytech Dept Elect Engn Tehran Iran Univ Sci & Technol Mazandaran Dept Comp Engn Behshahr Iran

Identification of drug -protein interactions plays an important role in drug discovery. Development of new calculation methods, which have high accuracy solve the problems related to the previous methods, which were expensive and time-consuming. In this article, a new model for drug -protein interactions, and a new mapping approach to represent drug -protein sequences are proposed. The proposed model consists of four parts: drug and protein descriptor section, Drug CNN and Protein CNN sections, Encoder section and classification section. In this method, first the data is prepared. At this stage, the totals are equal to each other. Then in the next step using the k-mers method and Chaos Game, the sequence of drug and protein becomes an image. In the next step, the image is used to train CNN models. These images serve as the input of independent networks for the drug and are considered as a protein. These networks are used to extract feature from drug and protein. In the last layer of these networks, features extracted from drug and protein sequences combine with each other. After concatenating, the number of features will raise. To reduce the number of features and to extract more efficient features, a variational autoencoder is used. In the last step, this combined feature vector is used to train machine learning models. The proposed method has been tested and evaluated on 6 standard data sets. The results of the experiments show that the proposed method has an acceptable performance compared to other methods in this data set.

关键词： Drug target interaction Multi source K-mers Chaos game Deep learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：