检索结果-内蒙古大学图书馆

Bayesian Multi-Temporal-Difference Learning

APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING 2022年第1期11卷

作者： Chien, Jen-Tzung Chiu, Yi-Chung Natl Yang Ming Chiao Tung Univ Inst Elect & Comp Engn Hsinchu Taiwan

This paper presents a new sequential learning via a planning strategy where the future samples are predicted by reflecting the past experiences. Such a strategy is appealing to implement an intelligent machine which foresees multiple time steps instead of predicting step by step. In particular, a flexible sequential learning is developed to directly predict future states without visiting all intermediate states. A Bayesian approach to multi-temporal-difference neural network is accordingly proposed to calculate the stochastic belief state for an abstract state machine so as to capture large-span context as well as make high-level prediction. Importantly, the sequence data are represented by multiple jumpy states with varying temporal differences. A Bayesian state machine is trained by maximizing the variational lower bound of log likelihood of sequence data. A generalized sequence model with various number of Markov states is derived with the simplified realization to the previous temporal-difference variational autoencoder. The predictive states are learned to roll forward with jumps. Experiments show that this approach is substantially trained to predict jumpy states in various types of sequence data.

关键词： Bayesian learning variational autoencoder sequential learning temporal-difference learning state machine

来源：评论

学校读者我要写书评

暂无评论

Direct feature extraction from two-dimensional X-ray diffraction images of semiconductor thin films for fabrication analysis

引用

SCIENCE AND TECHNOLOGY OF ADVANCED MATERIALS-METHODS 2022年第1期2卷 23-37页

作者： Yamashita, Akihiro Nagata, Takahiro Yagyu, Shinjiro Asahi, Toru Chikyow, Toyohiro Waseda Univ Dept Adv Sci & Engn Tokyo Japan Natl Inst Mat Sci Res & Serv Div Mat Data & Integrated Syst Tsukuba Japan Natl Inst Mat Sci Res Ctr Funct Mat 1-1 Namiki Tsukuba 3050044 Japan

We built a workflow for the fabrication analysis of thin films by applying machine-learning (ML) techniques directly to the measurement data. This will lower the problem in cost of synthesizing and analyzing samples to improve the fabrication conditions. The workflow combines two ML techniques: non-negative matrix factorization (NMF) and variational autoencoder (VAE). The measurement data were two-dimensional X-ray diffraction of indium-gallium oxide system thin films. The thin films were fabricated by physical vapor techniques under multiple conditions. First, the workflow was applied to the data of the thin films fabricated through pulsed laser deposition as a proof of concept. We found that our workflow extracted features that represented crystallinity differences in addition to substrate differences. Second, VAE was analyzed to determine whether it could generate new data from its latent space. The latent space of the VAE, which learned the extracted features, represented the relationship between the fabrication conditions such as laser intensities and crystallinity. Third, the inference ability of the new data fabricated through sputtering was evaluated. The capability of the workflow we confirmed will support researchers in improving fabrication conditions by visually comparing various fabricated samples.

关键词： Two-dimensional x-ray diffraction thin films machine learning feature extraction dimensionality reduction non-negative matrix factorization variational autoencoder Materials data analysis and utilization

来源：评论

学校读者我要写书评

暂无评论

Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network

引用

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2020年第8期26卷 2560-2575页

作者： Jiang, Boyi Zhang, Juyong Cai, Jianfei Zheng, Jianmin Univ Sci & Technol China Sch Math Sci Hefei 230052 Anhui Peoples R China Monash Univ Fac IT Clayton Vic 3800 Australia Nanyang Technol Univ Sch Engn & Comp Sci Singapore 639798 Singapore

Human bodies exhibit various shapes for different identities or poses, but the body shape has certain similarities in structure and thus can be embedded in a low-dimensional space. This article presents an autoencoder-like network architecture to learn disentangled shape and pose embedding specifically for the 3D human body. This is inspired by recent progress of deformation-based latent representation learning. To improve the reconstruction accuracy, we propose a hierarchical reconstruction pipeline for the disentangling process and construct a large dataset of human body models with consistent connectivity for the learning of the neural network. Our learned embedding can not only achieve superior reconstruction accuracy but also provide great flexibility in 3D human body generation via interpolation, bilinear interpolation, and latent space sampling. The results from extensive experiments demonstrate the powerfulness of our learned 3D human body embedding in various applications.

关键词： Shape Strain Three-dimensional displays Biological system modeling Computational modeling Solid modeling Face 3D body shape 3D human articulated body model variational autoencoder deformation representation hierarchical structure

来源：评论

学校读者我要写书评

暂无评论

Towards safe reinforcement-learning in industrial grid-warehousing

引用

INFORMATION SCIENCES 2020年 537卷 467-484页

作者： Andersen, Per-Arne Goodwin, Morten Granmo, Ole-Christoffer Univ Agder Dept ICT Jon Lilletuns Vei 9 N-4879 Grimstad Norway

Reinforcement learning has shown to be profoundly successful at learning optimal policies for simulated environments using distributed training with extensive compute capacity. Model-free reinforcement learning uses the notion of trial and error, where the error is a vital part of learning the agent to behave optimally. In mission-critical, real-world environments, there is little tolerance for failure and can cause damaging effects on humans and equipment. In these environments, current state-of-the-art reinforcement learning approaches are not sufficient to learn optimal control policies safely. On the other hand, model-based reinforcement learning tries to encode environment transition dynamics into a predictive model. The transition dynamics describes the mapping from one state to another, conditioned on an action. If this model is accurate enough, the predictive model is sufficient to train agents for optimal behavior in real environments. This paper presents the Dreaming variational autoencoder (DVAE) for safely learning good policies with a significantly lower risk of catastrophes occurring during training. The algorithm combines variational autoencoders, risk-directed exploration, and curiosity to train deep-q networks inside "dream" states. We introduce a novel environment, ASRS-Lab, for research in the safe learning of autonomous vehicles in grid-based warehousing. The work shows that the proposed algorithm has better sample efficiency with similar performance to novel model-free deep reinforcement learning algorithms while maintaining safety during training. (C) 2020 The Author(s). Published by Elsevier Inc.

关键词： Model-based reinforcement learning Neural networks variational autoencoder Markov decision processes Exploration Safe reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Scalable image generation and super resolution using generative adversarial networks

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GA...

引用

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY 2020年第2期35卷 953-966页

作者： Turhan, Ceren Guzel Bilge, Hasan Sakir Gazi Univ Comp Engn Dept TR-06570 Ankara Turkey Gazi Univ Elect Elect Engn Dept TR-06570 Ankara Turkey

Generative adversarial training has been one of the most active research topics and many researchers have conducted their studies on Generative Adversarial Network (GAN) shortly after it is claimed to be one of the most promising research area of the last decade by pioneers of the deep learning community. On the other hand, the idea behind generators has also reemerged autoencoder models such as variational autoencoder (VAE). Therefore, autoencoder models have gained their popularity back. Some restrictions of GAN models such as lack of inference mechanism, GAN and VAE based hybrid models have proposed addressing image generation. With the effect of these notions and studies, we have also considered VAE and GAN hybrid models. For obtaining synthetic but at the same time high-resolution handwritten-looking images without any training, Compositional Pattern Producing Network (CPPN) is adapted from previous studies for combining with VAE and adversarial training. For improving generation capabilities, an objective from a previous VAE/GAN model is also adapted for our VAE/CPGAN hybrid model. For analyzing the proposed model performance, baseline models such as GAN, VAE and VAE/GAN are also evaluated for comparisons. In this paper. it is clearly seen the proposed model is capable of the generating realistic and scalable super resolution synthetic images on a common dataset.

关键词： Deep learning variational autoencoder generative adversarial network image generation scalable super resolution

来源：评论

学校读者我要写书评

暂无评论

Enhancing Long Term Fairness in Recommendations with variational autoencoders 19

Enhancing Long Term Fairness in Recommendations with Variati...

引用

Proceedings of the 11th International Conference on Management of Digital EcoSystems

作者： Rodrigo Borges Kostas Stefanidis University of São Paulo & Tampere University São Paulo Brazil Tampere University Tampere Finland

ISBN: (纸本)9781450362382

Recommender systems have become indispensable for several Web sites, helping users deal with big amounts of data. They are capable of analyzing user/item interactions taking place on-line, and provide each user with a list of suggestions sorted by relevance. Items with the same or very close relevance, however, may occupy different positions in the ranking and may be exposed to completely different levels of attention. This promotes unfair treatment and can only be addressed by a long term *** autoencoders (VAEs) were recently proposed as the state-of-the-art for collaborative filtering recommendations, but as every other approach, they generate homogeneous prediction scores among the highest positions. In this paper, we propose incorporating randomness in the regular operation of VAEs in order to increase the fairness (mitigate the position bias) in multiple rounds of recommendation. We argue that adding a noise component when sampling values from VAE's latent representation provides long term fairness, despite of a tolerable decrease in ranking quality (NDCG). We calculate the trade-off between unfairness and NDCG when introducing 4 different noise *** solution has proved to be a very practical one and the results point for a clear positive effect of turning recommendation far more fair, despite some small NDCG loss in Movie Lens, Netflix and MSD datasets. In our best scenario, the unfairness was reduced by 76% despite a decrease of 5% in the quality of ranking.

关键词： Collaborative Filtering Recommendation Systems Position Bias variational autoencoder Fairness in Ranking

来源：评论

学校读者我要写书评

暂无评论

Exploiting Missing Value Patterns for a Backdoor Attack on Machine Learning Models of Electronic Health Records: Development and Validation Study

引用

JMIR MEDICAL INFORMATICS 2022年第8期10卷 e38440页

作者： Joe, Byunggill Park, Yonghyeon Hamm, Jihun Shin, Insik Lee, Jiyeon Korea Adv Inst Sci & Technol Sch Comp Daejeon South Korea Elect & Telecommun Res Inst Daejeon South Korea Tulane Univ Dept Comp Sci New Orleans LA 70118 USA Soongsil Univ Sch AI Convergence Seoul South Korea

Background: A backdoor attack controls the output of a machine learning model in 2 stages. First, the attacker poisons the training data set, introducing a back door into the victim's trained model. Second, during test time, the attacker adds an imperceptible pattern called a trigger to the input values, which forces the victim's model to output the attacker's intended values instead of true predictions or decisions. While backdoor attacks pose a serious threat to the reliability of machine learning-based medical diagnostics, existing backdoor attacks that directly change the input values are detectable relatively easily. Objective: The goal of this study was to propose and study a robust backdoor attack on mortality-prediction machine learning models that use electronic health records. We showed that our backdoor attack grants attackers full control over classification outcomes for safety-critical tasks such as mortality prediction, highlighting the importance of undertaking safe artificial intelligence research in the medical field. Methods: We present a trigger generation method based on missing patterns in electronic health record data. Compared to existing approaches, which introduce noise into the medical record, the proposed backdoor attack makes it simple to construct backdoor triggers without prior knowledge. To effectively avoid detection by manual inspectors, we employ variational autoencoders to learn the missing patterns in normal electronic health record data and produce trigger data that appears similar to this data. Results: We experimented with the proposed backdoor attack on 4 machine learning models (linear regression, multilayer perceptron, long short-term memory, and gated recurrent units) that predict in-hospital mortality using a public electronic health record data set. The results showed that the proposed technique achieved a significant drop in the victim's discrimination performance (reducing the area under the precision-recall curve by at

关键词： medical machine learning neural network mortality prediction backdoor attack electronic health record data Medical Information Mart for Intensive Care-III missing value mask meta-information variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

History matching of petroleum reservoirs using deep neural networks

引用

INTELLIGENT SYSTEMS WITH APPLICATIONS 2022年 16卷

作者： Alguliyev, Rasim Aliguliyev, Ramiz Imamverdiyev, Yadigar Sukhostat, Lyudmila Azerbaijan Natl Acad Sci Inst Informat Technol 9A B Vahabzade St Baku AZ1141 Azerbaijan

This paper proposes a novel approach based on deep learning to improve oil reservoirs' history matching problem. Deep autoencoders are widely used to solve the oil industry problems. However, as the input data increases, the autoencoder parameters increase exponentially. Our model is based on a convolutional variational autoencoder using AlexNet and bi-directional gated recurrent units. It parameterizes large-scale oilfield reservoirs. The proposed model is integrated into an ensemble smoother with multiple data assimilation to perform history matching. The proposed approach is validated on two reservoir models: PUNQ-S3 and Volve field. The root mean squared error, R2, and mean absolute error are calculated to verify the effectiveness of the proposed approach. The results show that the proposed model can effectively study the complex geological features of oil fields and be used in expert systems for reservoir modeling.

关键词： History matching AlexNet Bi-directional gated recurrent unit variational autoencoder Permeability Porosity

来源：评论

学校读者我要写书评

暂无评论

Deep Learning to Generate in Silico Chemical Property Libraries and Candidate Molecules for Small Molecule Identification in Complex Samples

引用

ANALYTICAL CHEMISTRY 2020年第2期92卷 1720-1729页

作者： Colby, Sean M. Nunez, Jamie R. Hodas, Nathan O. Corley, Courtney D. Renslow, Ryan R. Pacific Northwest Natl Lab Richland WA 99352 USA

Comprehensive and unambiguous identification of small molecules in complex samples will revolutionize our understanding of the role of metabolites in biological systems. Existing and emerging technologies have enabled measurement of chemical properties of molecules in complex mixtures and, in concert, are sensitive enough to resolve even stereoisomers. Despite these experimental advances, small molecule identification is inhibited by (i) chemical reference libraries (e.g., mass spectra, collision cross section, and other measurable property libraries) representing <1% of known molecules, limiting the number of possible identifications, and (ii) the lack of a method to generate candidate matches directly from experimental features (i.e., without a library). To this end, we developed a variational autoencoder (VAE) to learn a continuous numerical, or latent, representation of molecular structure to expand reference libraries for small molecule identification. We extended the VAE to include a chemical property decoder, trained as a multitask network, in order to shape the latent representation such that it assembles according to desired chemical properties. The approach is unique in its application to metabolomics and small molecule identification, with its focus on properties that can be obtained from experimental measurements (m/z, CCS) paired with its training paradigm, which involved a cascade of transfer learning iterations. First, molecular representation is learned from a large data set of structures with m/z labels. Next, in silico property values are used to continue training, as experimental property data is limited. Finally, the network is further refined by being trained with the experimental data. This allows the network to learn as much as possible at each stage, enabling success with progressively smaller data sets without overfitting. Once trained, the network can be used to predict chemical properties directly from structure, as well as generate candid

关键词： Transfer learning variational autoencoder Metabolomics Deep learning

来源：评论

学校读者我要写书评

暂无评论

On the Road With 16 Neurons: Towards Interpretable and Manipulable Latent Representations for Visual Predictions in Driving Scenarios

引用

IEEE ACCESS 2020年 8卷 179716-179734页

作者： Plebe, Alice Lio, Mauro Da Univ Trento Dept Informat Engn & Comp Sci I-38123 Trento Italy Univ Trento Dept Ind Engn I-38123 Trento Italy

This paper proposes a strategy for visual perception in the context of autonomous driving. Humans, when not distracted or drunk, are still the best drivers you can currently find. For this reason, we take inspiration from two theoretical ideas about the human mind and its neural organization. The first idea concerns how the brain uses structures of neuron ensembles that expand and compress information to extract abstract concepts from visual experience and code them into compact representations. The second idea suggests that these neural perceptual representations are not neutral but functional to predicting the future state of affairs in the environment. Similarly, the prediction mechanism is not neutral but oriented to the planning of future action. We identify within the deep learning framework two artificial counterparts of the aforementioned neurocognitive theories. We find a correspondence between the first theoretical idea and the architecture of convolutional autoencoders, while we translate the second theory into a training procedure that learns compact representations which are not neutral but oriented to driving tasks, from two distinct perspectives. From a static perspective, we force separate groups of neural units in the compact representations to represent specific concepts crucial to the driving task distinctly. From a dynamic perspective, we bias the compact representations to predict how the current road scenario will change in the future. We successfully learn compact representations that use as few as 16 neural units for each of the two basic driving concepts we consider: cars and lanes. We maintain the two concepts separated in the latent space to facilitate the interpretation and manipulation of the perceptual representations. The source code for this paper is available at https://***/3lis/rnn_vae.

关键词： Task analysis Neurons Roads Computational modeling Autonomous vehicles Visualization Machine learning Autonomous driving convergence-divergence zones deep learning predictive brain 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：