检索结果-内蒙古大学图书馆

IEEE OPEN JOURNAL OF CIRCUITS AND SYSTEMS 2021年 2卷 627-632页

作者： Zan, Zhao Liu, Chao Sun, Heming Zeng, Xiaoyang Fan, Yibo Fudan Univ Coll Microelect State Key Lab ASIC & Syst Shanghai 200000 Peoples R China Waseda Univ Waseda Res Inst Sci & Engn Tokyo 1698555 Japan PRESTO JST Kawaguchi Saitama 3320012 Japan ZTE Corp State Key Lab Mobile Network & Mobile Multimedia Shenzhen 518057 Peoples R China

Learned image compression techniques have achieved considerable development in recent years. In this paper, we find that the performance bottleneck lies in the use of a single hyperprior decoder, in which case the ternary Gaussian model collapses to a binary one. To solve this, we propose to use three hyperprior decoders to separate the decoding process of the mixed parameters in discrete Gaussian mixture likelihoods, achieving more accurate parameters estimation. Experimental results demonstrate the proposed method optimized by MS-SSIM achieves on average 3.36% BD-rate reduction compared with state-of-the-art approach. The contribution of the proposed method to the coding time and FLOPs is negligible.

关键词： Measurement Image coding Parameter estimation Costs Circuits and systems Mixture models Decoding Learned image compression variational autoencoder convolutional neural networks Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring

引用

SENSORS 2023年第3期23卷 1061页

作者： Paepae, Thulane Bokoro, Pitshou N. Kyamakya, Kyandoghere Univ Johannesburg Dept Elect & Elect Engn Technol ZA-2028 Doornfontein South Africa Alpen Adria Univ Klagenfurt Inst Smart Syst Technol Transportat Informat A-9020 Klagenfurt Austria Univ Kinshasa Fac Polytech PO Box 127 11 Kinshasa DEM REP CONGO

To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables as inputs. While the predictive performance of these data-driven, virtual-sensor models depends on the use of adequate training samples (in quality and quantity), the procurement and operational cost of nitrogen and phosphorus sensors make it impractical to acquire sufficient samples. For this reason, the variational autoencoder, which is one of the most prominent methods in generative models, was utilized in the present work for generating synthetic data. The generation capacity of the model was verified using water-quality data from two tributaries of the River Thames in the United Kingdom. Compared to the current state of the art, our novel data augmentation-including proper experimental settings or hyperparameter optimization-improved the root mean squared errors by 23-63%, with the most significant improvements observed when up to three predictors were used. In comparing the predictive algorithms' performances (in terms of the predictive accuracy and computational cost), k-nearest neighbors and extremely randomized trees were the best-performing algorithms on average.

关键词： water-quality monitoring eutrophication synthetic data soft sensor surrogate variables variational autoencoder machine learning deep neural network parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Learning disentangled skills for hierarchical reinforcement learning through trajectory autoencoder with weak labels

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期230卷

作者： Song, Wonil Jeon, Sangryul Choi, Hyesong Sohn, Kwanghoon Min, Dongbo Yonsei Univ Sch Elect & Elect Engn Seoul South Korea Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA Ewha Womans Univ Dept Comp Sci & Engn Seoul 03760 South Korea Korea Inst Sci & Technol KIST Seoul 02792 South Korea

Typically, hierarchical reinforcement learning (RL) requires skills that are applicable to various downstream tasks. Although several recent studies have proposed the supervised and unsupervised learning of such skills, the learned skills are often entangled, which hinders their interpretation. To alleviate this, we propose a novel method to use weak labels for learning disentangled skills from the continuous latent representations of trajectories. To this end, we extended a trajectory variational autoencoder (VAE) to impose an inductive bias using weak labels, which explicitly enforces the disentangling of the trajectory representations into factors of interest intended for the model to learn. Using the latent representations as skills, a skill-based policy network is trained to generate trajectories similar to the learned decoder of the trajectory VAE. Furthermore, using the disentangled skill, we propose a skill repetition that can expand the entire trajectories generated by the policy at test time, resulting in an effective planning strategy. Experiments were performed on several challenging navigation tasks in mazes, and the results demonstrate the effectiveness of our method at solving hierarchical RL problems even with a long horizon and sparse rewards.

关键词： Deep reinforcement learning Hierarchical reinforcement learning Skill learning variational autoencoder Disentangled representation Weak label Planning

来源：评论

学校读者我要写书评

暂无评论

GenSMILES: An enhanced validity conscious representation for inverse design of molecules

引用

KNOWLEDGE-BASED SYSTEMS 2023年 268卷

作者： Bhadwal, Arun Singh Kumar, Kamal Kumar, Neeraj Natl Inst Technol Srinagar 246174 Uttaranchal India Thapar Inst Engn & Technol Patiala 147004 Punjab India Lebanese Amer Univ Dept Elect & Comp Engn Beirut 11022801 Lebanon King Abdulaziz Univ Fac Comp & IT Jeddah 22233 Saudi Arabia Univ Petr & Energy Studies Sch Comp Sci Dehra Dun 248007 Uttaranchal India Chandigarh Univ Dept Comp Sci & Engn Gharuan Mohali 140413 Punjab India

Deep neural networks have become increasingly important in recent years for creating molecules with desirable properties. In general, SMILES strings are used to train deep neural network based models. The trained model is then used to generate the desired molecules. Unfortunately, due to syntactical and semantic flaws in the representation, the SMILES string generates a substantial number of invalid molecules. SMILES representation fails to efficiently handle rings, branch and bonds between atoms. Lack of robustness in dealing with the cited aspects results in abundance of invalid strings. To overcome this limitation, this paper proposes a SMILES like representation, called GenSMILES. GenSMILES tackles syntactical and semantic issues by relying upon derivative rules to apply constraints. This causes a generative model produces more valid SMILES strings. By substituting a single notation for the pair representation of branches and rings in SMILES with a ) and boolean AND, respectively, GenSMILES corrects the syntactical issues. The mismatching of atom's bonds is the main cause of semantic errors. GenSMILES addresses such issues by employing derivation rules during string conversion from GenSMILES to SMILES. Every SMILES string can be represented with an equivalent GenSMILES. When used for designing drug molecule, GenSMILES increases molecule's validity when compared with SMILES and DeepSMILES on two popular architectures i.e., Recurrent Neural Network and variational autoencoder. The main benefit of GenSMILES is that it can be applied directly to generative algorithms without adapting the model environment. GenSMILES is beneficial not only to generative approaches of DL but also to the approaches that use SMILES string-like representation. On most of the datasets, GenSMILES is effective in improving validity above 90% and diversity score 15. GenSMILES results in more diversity in the properties of generated molecules and allows exploration of larger portion of undisc

关键词： SMILES GenSMILES DeepSMILES Deep learning Recurrent neural network variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Performance-Based Generative Design for Parametric Modeling of Engineering Structures Using Deep Conditional Generative Models

引用

AUTOMATION IN CONSTRUCTION 2023年 156卷

作者： Bucher, Martin Juan Jose Kraus, Michael Anton Rust, Romana Tang, Siyu Swiss Fed Inst Technol Stefano Franscini Pl CH-8093 Zurich Switzerland

Parametric Modeling, Generative Design, and Performance-Based Design have gained increasing attention in the AEC field as a way to create a wide range of design variants while focusing on performance attributes rather than building codes. However, the relationships between design parameters and performance attributes are often very complex, resulting in a highly iterative and unguided process. In this paper, we argue that a more goal-oriented design process is enabled by an inverse formulation that starts with performance attributes instead of design parameters. A Deep Conditional Generative Design workflow is proposed that takes a set of performance attributes and partially defined design features as input and produces a complete set of design parameters as output. A model architecture based on a Conditional variational autoencoder is presented along with different approximate posteriors, and evaluated on four different case studies. Compared to Genetic Algorithms, our method proves superior when utilizing a pre-trained model.

关键词： Deep generative modeling Performance-based design Generative design variational autoencoder Deep generative design Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Unsupervised Intrusion Detection Model Based on variational Auto-Encoder

引用

SENSORS 2023年第20期23卷 8407页

作者： Ren, Yi Feng, Kanghui Hu, Fei Chen, Liangyin Chen, Yanru Sichuan Univ Sch Comp Sci Chengdu 610065 Peoples R China Sichuan Univ Inst Ind Internet Res Chengdu 610065 Peoples R China

With the gradual integration of internet technology and the industrial control field, industrial control systems (ICSs) have begun to access public networks on a large scale. Attackers use these public network interfaces to launch frequent invasions of industrial control systems, thus resulting in equipment failure and downtime, production data leakage, and other serious harm. To ensure security, ICSs urgently need a mature intrusion detection mechanism. Most of the existing research on intrusion detection in ICSs focuses on improving the accuracy of intrusion detection, thereby ignoring the problem of limited equipment resources in industrial control environments, which makes it difficult to apply excellent intrusion detection algorithms in practice. In this study, we first use the spectral residual (SR) algorithm to process the data;we then propose the improved lightweight variational autoencoder (LVA) with autoregression to reconstruct the data, and we finally perform anomaly determination based on the permutation entropy (PE) algorithm. We construct a lightweight unsupervised intrusion detection model named LVA-SP. The model as a whole adopts a lightweight design with a simpler network structure and fewer parameters, which achieves a balance between the detection accuracy and the system resource overhead. Experimental results on the ICSs dataset show that our proposed LVA-SP model achieved an F1-score of 84.81% and has advantages in terms of time and memory overhead.

关键词： industrial control systems intrusion detection variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Graph-based Embedding for Neural Architecture Search

引用

Procedia Computer Science 2023年 229卷 47-54页

作者： Evgeny Bessonnitsyn Vsevolod Shaldin Valeria Efimova Viacheslav Shalamov ITMO University Kronverksky Pr. 49 bldg. A St. Petersburg 197101 Russia

Recently, network architecture search is gaining popularity. The neural network representation as a directed acyclic graph is considered for subsequent architecture optimization. Currently, most of the existing encoders rely only on the model layer properties and do not take into account the attributes of layers. This work proposes an algorithm for mapping a CNN network to a vector space considering the layer attributes, such as different dimensions of a particular layer. The proposed algorithm was compared with D-VAE and DVAE-EMB and showed less information loss caused by the mapping of a network to a vector space. As the results show, the performance of the model was shown after direct conversion to embedding and reverse conversion to architecture. The method allows more accurate neural network architecture mapping into a vector form, which will improve the search for the best architecture. The method implementation is publicly available at https://***/Turukmokto/GraphEmbedding-dev .

关键词： neural network architecture search vector representation variational autoencoder graphs with attributes

来源：评论

学校读者我要写书评

暂无评论

Exploring semi-supervised variational autoencoders for biomedical relation extraction

引用

METHODS 2019年 166卷 112-119页

作者： Zhang, Yijia Lu, Zhiyong NIH NCBI NLM Bethesda MD 20894 USA Dalian Univ Technol Sch Comp Sci & Technol Dalian 116023 Liaoning Peoples R China

The biomedical literature provides a rich source of knowledge such as protein-protein interactions (PPIs), drug-drug interactions (DDIs) and chemical-protein interactions (CPIs). Biomedical relation extraction aims to automatically extract biomedical relations from biomedical text for various biomedical research. State-of-the-art methods for biomedical relation extraction are primarily based on supervised machine learning and therefore depend on (sufficient) labeled data. However, creating large sets of training data is prohibitively expensive and labor-intensive, especially so in biomedicine as domain knowledge is required. In contrast, there is a large amount of unlabeled biomedical text available in PubMed. Hence, computational methods capable of employing unlabeled data to reduce the burden of manual annotation are of particular interest in biomedical relation extraction. We present a novel semi-supervised approach based on variational autoencoder (VAE) for biomedical relation extraction. Our model consists of the following three parts, a classifier, an encoder and a decoder. The classifier is implemented using multi-layer convolutional neural networks (CNNs), and the encoder and decoder are implemented using both bidirectional long short-term memory networks (Bi-LSTMs) and CNNs, respectively. The semi-supervised mechanism allows our model to learn features from both the labeled and unlabeled data. We evaluate our method on multiple public PPI, DDI and CPI corpora. Experimental results show that our method effectively exploits the unlabeled data to improve the performance and reduce the dependence on labeled data. To our best knowledge, this is the first semi-supervised VAE-based method for (biomedical) relation extraction. Our results suggest that exploiting such unlabeled data can be greatly beneficial to improved performance in various biomedical relation extraction, especially when only limited labeled data (e.g. 2000 samples or less) is available in such ta

关键词： Biomedical literature Relation extraction Semi-supervised learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Discovering influential factors in variational autoencoders

引用

PATTERN RECOGNITION 2020年 100卷 107166-107166页

作者： Liu, Shiqi Liu, Jingxin Zhao, Qian Cao, Xiangyong Li, Huibin Meng, Deyu Meng, Hongying Liu, Sheng Xi An Jiao Tong Univ Xian Shaanxi Peoples R China Brunel Univ London London England SUNY Buffalo Buffalo NY 14214 USA

In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variational autoencoder (VAE). The VAE is proposed to learn independent low dimension representation while facing the problem that sometimes pre-set factors are ignored. We argue that the mutual information of the input and each learned factor of the representation plays a necessary indicator of discovering the influential factors. We find the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore result in some non-influential factors whose function on data reconstruction could be ignored. We show mutual information also influences the lower bound of VAE's reconstruction error and downstream classification task. To make such indicator applicable, we design an algorithm for calculating the mutual information for VAE and prove its consistency. Experimental results on MNIST, CelebA and DEAP datasets show that mutual information can help determine influential factors, of which some are interpretable and can be used to further generation and classification tasks, and help discover the variant that connects with emotion on DEAP dataset. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： variational autoencoder Mutual information Generative model

来源：评论

学校读者我要写书评

暂无评论

Experimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environments

Experimental Evidence that Empowerment May Drive Exploration...

引用

IEEE International Conference on Development and Learning (ICDL)

作者： Massari, Francesco Biehl, Martin Meeden, Lisa Kanai, Ryota Swarthmore Coll Swarthmore PA 19081 USA Araya Inc Tokyo Japan Swarthmore Coll Dept Comp Sci Swarthmore PA 19081 USA

ISBN: (纸本)9781728162423

Reinforcement Learning (RL) is known to be often unsuccessful in environments with sparse extrinsic rewards. A possible countermeasure is to endow RL agents with an intrinsic reward function, or 'intrinsic motivation', which rewards the agent based on certain features of the current sensor state. An intrinsic reward function based on the principle of empowerment assigns rewards proportional to the amount of control the agent has over its own sensors. We implemented a variation on a recently proposed intrinsically motivated agent, which we refer to as the 'curious' agent, and an empowerment-inspired agent. The former leverages sensor state encoding with a variational autoencoder, while the latter predicts the next sensor state via a variational information bottleneck. We compared the performance of both agents to that of an advantage actor-critic baseline in four sparse reward grid worlds. Both the empowerment agent and its curious competitor seem to benefit to similar extents from their intrinsic rewards. This provides some experimental support to the conjecture that empowerment can be used to drive exploration.

关键词： Advantage Actor-Critic Empowerment Information Bottleneck Information Gain Intrinsic Motivation Reinforcement 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：