Articles de revues : « Deep generative modeling »

1

Blaschke, Thomas, et Jürgen Bajorath. « Compound dataset and custom code for deep generative multi-target compound design ». Future Science OA 7, n^o 6 (juillet 2021) : FSO715. http://dx.doi.org/10.2144/fsoa-2021-0033.

Texte intégral

Résumé :

Aim: Generating a data and software infrastructure for evaluating multi-target compound (MT-CPD) design via deep generative modeling. Methodology: The REINVENT 2.0 approach for generative modeling was extended for MT-CPD design and a large benchmark data set was curated. Exemplary results & data: Proof-of-concept for deep generative MT-CPD design was established. Custom code and the benchmark set comprising 2809 MT-CPDs, 61,928 single-target and 295,395 inactive compounds from biological screens are made freely available. Limitations & next steps: MT-CPD design via deep learning is still at its conceptual stages. It will be required to demonstrate experimental impact. The data and software we provide enable further investigation of MT-CPD design and generation of candidate molecules for experimental programs.

Styles APA, Harvard, Vancouver, ISO, etc.

2

Joshi, Ameya, Minsu Cho, Viraj Shah, Balaji Pokuri, Soumik Sarkar, Baskar Ganapathysubramanian et Chinmay Hegde. « InvNet : Encoding Geometric and Statistical Invariances in Deep Generative Models ». Proceedings of the AAAI Conference on Artificial Intelligence 34, n^o 04 (3 avril 2020) : 4377–84. http://dx.doi.org/10.1609/aaai.v34i04.5863.

Texte intégral

Résumé :

Generative Adversarial Networks (GANs), while widely successful in modeling complex data distributions, have not yet been sufficiently leveraged in scientific computing and design. Reasons for this include the lack of flexibility of GANs to represent discrete-valued image data, as well as the lack of control over physical properties of generated samples. We propose a new conditional generative modeling approach (InvNet) that efficiently enables modeling discrete-valued images, while allowing control over their parameterized geometric and statistical properties. We evaluate our approach on several synthetic and real world problems: navigating manifolds of geometric shapes with desired sizes; generation of binary two-phase materials; and the (challenging) problem of generating multi-orientation polycrystalline microstructures.

Styles APA, Harvard, Vancouver, ISO, etc.

3

Lai, Peter, et Feruza Amirkulova. « Acoustic metamaterial design using Conditional Wasserstein Generative Adversarial Networks ». Journal of the Acoustical Society of America 151, n^o 4 (avril 2022) : A253. http://dx.doi.org/10.1121/10.0011234.

Texte intégral

Résumé :

This talk presents a method for generating planar configurations of scatterers with a reduced total scattering cross section (TSCS) by means of generative modeling and deep learning. The TSCS minimization via repeated forward modeling techniques, trial-error methods, and traditional optimization methods requires considerable computer resources and time. However, similar or better results can be achieved more efficiently by training a deep learning model to generate such optimized configurations producing low scattering effect. In this work, the Conditional Wasserstein Generative Adversarial Networks (cWGAN) is combined with Convolutional Neural Networks (CNN) to create the generative modeling architecture [1]. The generative model is implemented with a conditional proponent to allow the TSCS targeted design generation and is enhanced with the coordinate convolution (CordConv) layer to improve the model’s spatial recognition of cylinder configurations. The cWGAN model [1] is capable of generating images of 2D configurations of scatterers that exhibit low scattering. The method is demonstrated by giving examples of generating 2-cylinder and 4-cylinder planar configurations with minimal TSCS. [1]. P. Lai, F. Amirkulova, and P. Gerstoft. “Conditional Wasserstein generative adversarial networks applied to acoustic metamaterial design,” J. Acoust. Soc. Am. 150(6), 4362–4374 (2021).

Styles APA, Harvard, Vancouver, ISO, etc.

4

Strokach, Alexey, et Philip M. Kim. « Deep generative modeling for protein design ». Current Opinion in Structural Biology 72 (février 2022) : 226–36. http://dx.doi.org/10.1016/j.sbi.2021.11.008.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

5

Lopez, Romain, Jeffrey Regier, Michael B. Cole, Michael I. Jordan et Nir Yosef. « Deep generative modeling for single-cell transcriptomics ». Nature Methods 15, n^o 12 (30 novembre 2018) : 1053–58. http://dx.doi.org/10.1038/s41592-018-0229-2.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

6

Lee, Ung-Gi, Sang-Hee Kang, Jong-Chan Lee, Seo-Yeon Choi, Ukmyung Choi et Cheol-Il Lim. « Development of Deep Learning-based Art Learning Support Tool : Using Generative Modeling ». Korean Association for Educational Information and Media 26, n^o 1 (31 mars 2020) : 207–36. http://dx.doi.org/10.15833/kafeiam.26.1.207.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

7

Behnia, Farnaz, Dominik Karbowski et Vadim Sokolov. « Deep generative models for vehicle speed trajectories ». Applied Stochastic Models in Business and Industry 39, n^o 5 (septembre 2023) : 701–19. http://dx.doi.org/10.1002/asmb.2816.

Texte intégral

Résumé :

AbstractGenerating realistic vehicle speed trajectories is a crucial component in evaluating vehicle fuel economy and in predictive control of self‐driving cars. Traditional generative models rely on Markov chain methods and can produce accurate synthetic trajectories but are subject to the curse of dimensionality. They do not allow to include conditional input variables into the generation process. In this paper, we show how extensions to deep generative models allow accurate and scalable generation. Proposed architectures involve recurrent and feed‐forward layers and are trained using adversarial techniques. Our models are shown to perform well on generating vehicle trajectories using a model trained on GPS data from Chicago metropolitan area.

Styles APA, Harvard, Vancouver, ISO, etc.

8

Janson, Giacomo, et Michael Feig. « Transferable deep generative modeling of intrinsically disordered protein conformations ». PLOS Computational Biology 20, n^o 5 (23 mai 2024) : e1012144. http://dx.doi.org/10.1371/journal.pcbi.1012144.

Texte intégral

Résumé :

Intrinsically disordered proteins have dynamic structures through which they play key biological roles. The elucidation of their conformational ensembles is a challenging problem requiring an integrated use of computational and experimental methods. Molecular simulations are a valuable computational strategy for constructing structural ensembles of disordered proteins but are highly resource-intensive. Recently, machine learning approaches based on deep generative models that learn from simulation data have emerged as an efficient alternative for generating structural ensembles. However, such methods currently suffer from limited transferability when modeling sequences and conformations absent in the training data. Here, we develop a novel generative model that achieves high levels of transferability for intrinsically disordered protein ensembles. The approach, named idpSAM, is a latent diffusion model based on transformer neural networks. It combines an autoencoder to learn a representation of protein geometry and a diffusion model to sample novel conformations in the encoded space. IdpSAM was trained on a large dataset of simulations of disordered protein regions performed with the ABSINTH implicit solvent model. Thanks to the expressiveness of its neural networks and its training stability, idpSAM faithfully captures 3D structural ensembles of test sequences with no similarity in the training set. Our study also demonstrates the potential for generating full conformational ensembles from datasets with limited sampling and underscores the importance of training set size for generalization. We believe that idpSAM represents a significant progress in transferable protein ensemble modeling through machine learning.

Styles APA, Harvard, Vancouver, ISO, etc.

9

Zhang, Chun, Liangxu Xie, Xiaohua Lu, Rongzhi Mao, Lei Xu et Xiaojun Xu. « Developing an Improved Cycle Architecture for AI-Based Generation of New Structures Aimed at Drug Discovery ». Molecules 29, n^o 7 (27 mars 2024) : 1499. http://dx.doi.org/10.3390/molecules29071499.

Texte intégral

Résumé :

Drug discovery involves a crucial step of optimizing molecules with the desired structural groups. In the domain of computer-aided drug discovery, deep learning has emerged as a prominent technique in molecular modeling. Deep generative models, based on deep learning, play a crucial role in generating novel molecules when optimizing molecules. However, many existing molecular generative models have limitations as they solely process input information in a forward way. To overcome this limitation, we propose an improved generative model called BD-CycleGAN, which incorporates BiLSTM (bidirectional long short-term memory) and Mol-CycleGAN (molecular cycle generative adversarial network) to preserve the information of molecular input. To evaluate the proposed model, we assess its performance by analyzing the structural distribution and evaluation matrices of generated molecules in the process of structural transformation. The results demonstrate that the BD-CycleGAN model achieves a higher success rate and exhibits increased diversity in molecular generation. Furthermore, we demonstrate its application in molecular docking, where it successfully increases the docking score for the generated molecules. The proposed BD-CycleGAN architecture harnesses the power of deep learning to facilitate the generation of molecules with desired structural features, thus offering promising advancements in the field of drug discovery processes.

Styles APA, Harvard, Vancouver, ISO, etc.

10

Guliev, R. « Generative adversarial networks for modeling reservoirs with permeability anisotropy ». IOP Conference Series : Materials Science and Engineering 1201, n^o 1 (1 novembre 2021) : 012066. http://dx.doi.org/10.1088/1757-899x/1201/1/012066.

Texte intégral

Résumé :

Abstract The geological model is a main element in describing the characteristics of hydrocarbon reservoirs. These models are usually obtained using geostatistical modeling techniques. Recently, methods based on deep learning algorithms have begun to be applied as a generator of a geologic models. However, there are still problems with how to assimilate dynamic data to the model. The goal of this work was to develop a deep learning algorithm - generative adversarial network (GAN) and demonstrate the process of generating a synthetic geological model: • Without integrating permeability data into the model • With data assimilation of well permeability data into the model The authors also assessed the possibility of creating a pair of generative-adversarial network-ensemble smoother to improve the closed-loop reservoir management of oil field development.

Styles APA, Harvard, Vancouver, ISO, etc.

11

Li, Guangyu, Bo Jiang, Hao Zhu, Zhengping Che et Yan Liu. « Generative Attention Networks for Multi-Agent Behavioral Modeling ». Proceedings of the AAAI Conference on Artificial Intelligence 34, n^o 05 (3 avril 2020) : 7195–202. http://dx.doi.org/10.1609/aaai.v34i05.6209.

Texte intégral

Résumé :

Understanding and modeling behavior of multi-agent systems is a central step for artificial intelligence. Here we present a deep generative model which captures behavior generating process of multi-agent systems, supports accurate predictions and inference, infers how agents interact in a complex system, as well as identifies agent groups and interaction types. Built upon advances in deep generative models and a novel attention mechanism, our model can learn interactions in highly heterogeneous systems with linear complexity in the number of agents. We apply this model to three multi-agent systems in different domains and evaluate performance on a diverse set of tasks including behavior prediction, interaction analysis and system identification. Experimental results demonstrate its ability to model multi-agent systems, yielding improved performance over competitive baselines. We also show the model can successfully identify agent groups and interaction types in these systems. Our model offers new opportunities to predict complex multi-agent behaviors and takes a step forward in understanding interactions in multi-agent systems.

Styles APA, Harvard, Vancouver, ISO, etc.

12

Drygala, C., B. Winhart, F. di Mare et H. Gottschalk. « Generative modeling of turbulence ». Physics of Fluids 34, n^o 3 (mars 2022) : 035114. http://dx.doi.org/10.1063/5.0082562.

Texte intégral

Résumé :

We present a mathematically well-founded approach for the synthetic modeling of turbulent flows using generative adversarial networks (GAN). Based on the analysis of chaotic, deterministic systems in terms of ergodicity, we outline a mathematical proof that GAN can actually learn to sample state snapshots from the invariant measure of the chaotic system. Based on this analysis, we study a hierarchy of chaotic systems starting with the Lorenz attractor and then carry on to the modeling of turbulent flows with GAN. As training data, we use fields of velocity fluctuations obtained from large-eddy simulations (LES). Two architectures are investigated in detail: we use a deep, convolutional GAN (DCGAN) to synthesize the turbulent flow around a cylinder. We furthermore simulate the flow around a low-pressure turbine stator using the pix2pixHD architecture for a conditional DCGAN being conditioned on the position of a rotating wake in front of the stator. The settings of adversarial training and the effects of using specific GAN architectures are explained. We thereby show that GAN are efficient in simulating turbulence in technically challenging flow problems on the basis of a moderate amount of training data. GAN training and inference times significantly fall short when compared with classical numerical methods, in particular, LES, while still providing turbulent flows in high resolution. We furthermore analyze the statistical properties of the synthesized and LES flow fields, which agree excellently. We also show the ability of the conditional GAN to generalize over changes of geometry by generating turbulent flow fields for positions of the wake that are not included in the training data.

Styles APA, Harvard, Vancouver, ISO, etc.

13

Qiu, Cheng, Anam Abbas et Feruza Amirkulova. « Pentamode metamaterial design via generative modeling and deep learning ». Journal of the Acoustical Society of America 151, n^o 4 (avril 2022) : A255. http://dx.doi.org/10.1121/10.0011241.

Texte intégral

Résumé :

In this talk, the deep learning-assisted models will be presented for the design of pentamode unit cells to construct a 3-D lattice structure that can mimic the acoustic properties of water. The pentamode models were implemented and modified by altering the properties of the structure during the full-wave simulation performed on COMSOL Multiphysics software to ensure they meet the requirements of specific appliances for manufacture. The design is further improved by the inverse design technique. The implementation of conditional Wasserstein Generative Adversarial Networks with gradient penalty (cWGAN-GP) for the inverse design will be illustrated by showing examples of 3-D titanium pentamode structures on the hexagonal lattice. The cWGAN was set up using critic and generator with CoordConv layers, along with regressor to produce images matching the desired labels. The convolutional neural network was used as an auxiliary regressor to predict all design parameters for the cell images. The expected PM lattice structure has a high bulk modulus, low-shear modulus and behaves as metal water at a broad range of frequencies including higher frequencies.

Styles APA, Harvard, Vancouver, ISO, etc.

14

Veres, Matthew, Medhat Moussa et Graham W. Taylor. « Modeling Grasp Motor Imagery Through Deep Conditional Generative Models ». IEEE Robotics and Automation Letters 2, n^o 2 (avril 2017) : 757–64. http://dx.doi.org/10.1109/lra.2017.2651945.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

15

Zhang, Zaiwei, Zhenpei Yang, Chongyang Ma, Linjie Luo, Alexander Huth, Etienne Vouga et Qixing Huang. « Deep Generative Modeling for Scene Synthesis via Hybrid Representations ». ACM Transactions on Graphics 39, n^o 2 (14 avril 2020) : 1–21. http://dx.doi.org/10.1145/3381866.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

16

Wang, Yong, Guoliang Li, Kaiyu Li et Haitao Yuan. « A Deep Generative Model for Trajectory Modeling and Utilization ». Proceedings of the VLDB Endowment 16, n^o 4 (décembre 2022) : 973–85. http://dx.doi.org/10.14778/3574245.3574277.

Texte intégral

Résumé :

Modern location-based systems have stimulated explosive growth of urban trajectory data and promoted many real-world applications, e.g. , trajectory prediction. However, heavy big data processing overhead and privacy concerns hinder trajectory acquisition and utilization. Inspired by regular trajectory distribution on transportation road networks, we propose to model trajectory data privately with a deep generative model and leverage the model to generate representative trajectories for downstream tasks or directly support these tasks ( e.g. , popularity ranking), rather than acquiring and processing the original big trajectory data. Nevertheless, it is rather challenging to model high-dimensional trajectories with time-varying yet skewed distribution. To address this problem, we model and generate trajectory sequence with judiciously encoded spatio-temporal features over skewed distribution by leveraging an important factor neglected by the literature - the underlying road properties ( e.g. , road types and directions), which are closely related to trajectory distribution. Specifically, we decompose trajectory into map-matched road sequence with temporal information and embed them to encode spatio-temporal features. Then, we enhance trajectory representation by encoding inherent route planning patterns from the underlying road properties. Later, we encode spatial correlations among edges and daily and weekly temporal periodicity information. Next, we employ a meta-learning module to generate trajectory sequence step by step by learning generalized trajectory distribution patterns from skewed trajectory data based on the well-encoded trajectory prefix. Last but not least, we preserve trajectory privacy by learning the model differential privately with clipping gradients. Experiments on real-world datasets show that our method significantly outperforms existing methods.

Styles APA, Harvard, Vancouver, ISO, etc.

17

Martínez-Palomera, Jorge, Joshua S. Bloom et Ellianna S. Abrahams. « Deep Generative Modeling of Periodic Variable Stars Using Physical Parameters ». Astronomical Journal 164, n^o 6 (30 novembre 2022) : 263. http://dx.doi.org/10.3847/1538-3881/ac9b3f.

Texte intégral

Résumé :

Abstract The ability to generate physically plausible ensembles of variable sources is critical to the optimization of time domain survey cadences and the training of classification models on data sets with few to no labels. Traditional data augmentation techniques expand training sets by reenvisioning observed exemplars, seeking to simulate observations of specific training sources under different (exogenous) conditions. Unlike fully theory-driven models, these approaches do not typically allow principled interpolation nor extrapolation. Moreover, the principal drawback of theory-driven models lies in the prohibitive computational cost of simulating source observables from ab initio parameters. In this work, we propose a computationally tractable machine learning approach to generate realistic light curves of periodic variables capable of integrating physical parameters and variability classes as inputs. Our deep generative model, inspired by the transparent latent space generative adversarial networks, uses a variational autoencoder (VAE) architecture with temporal convolutional network layers, trained using the OGLE-III optical light curves and physical characteristics (e.g., effective temperature and absolute magnitude) from Gaia DR2. A test using the temperature–shape relationship of RR Lyrae demonstrates the efficacy of our generative “physics-enhanced latent space VAE” (PELS-VAE) model. Such deep generative models, serving as nonlinear nonparametric emulators, present a novel tool for astronomers to create synthetic time series over arbitrary cadences.

Styles APA, Harvard, Vancouver, ISO, etc.

18

Amirkulova, Feruza, Linwei Zhou, Anam Abbas, Peter Lai, Cheng Qiu et Tristan A. Shah. « Acoustic metamaterial design framework using deep learning and generative modeling ». Journal of the Acoustical Society of America 151, n^o 4 (avril 2022) : A253. http://dx.doi.org/10.1121/10.0011233.

Texte intégral

Résumé :

This talk presents our findings and research performed on the application of deep learning and generative modeling in acoustic metamaterial design. Specifically, we will discuss our research findings published in recent papers on the application of deep learning algorithms, generative neural networks, reinforcement learning models, and global optimization for the inverse design of 2-D and 3-D acoustic metamaterial structures. The examples will be shown for the implementation of neural networks models for the inverse design of 3-D pentamode structures resulting in a low shear modulus, high bulk modulus, and an impedance matched with water. The generative 2-D GLO-Nets and the reinforcement learning models producing broadband low scattering effects for 2-D planar configurations of scatterers under plane wave incidence will be presented. The current challenges encountered during the application of deep learning methods in scaled metamaterial design will be discussed.

Styles APA, Harvard, Vancouver, ISO, etc.

19

Wang, Wei-Ching. « Sound localization via deep learning, generative modeling, and global optimization ». Journal of the Acoustical Society of America 151, n^o 4 (avril 2022) : A255. http://dx.doi.org/10.1121/10.0011240.

Texte intégral

Résumé :

An acoustic lens is capable of focusing incident plane waves at the focal point. This talk will discuss a new approach to design metamaterials with a focusing effect using effective and innovative methods by using machine learning. Specifically, the physics simulations use multiple scattering theory and machine learning techniques such as deep learning and generative modeling. The 2-D-Global Optimization Networks (2-D-GLOnets) model [1] developed initially for acoustic cloak design is adapted and generalized to design and optimize the acoustic lens. We supply the absolute pressure amplitude and gradient into the deep learning algorithms to discover the optimal scatterer positions that maximize the absolute pressure at the focal point in the confined region. We examine and evaluate the performance of the generative network, searching for an optimal configuration of scatterers over a range of parameters to produce desired features, such as broadband focusing and localization effects. The model will show examples of planar configurations of cylindrical structures producing focusing effect. [1] L. Zhuo and F. Amirkulova, “Design of acoustic cloak using generative modeling and gradient-based optimization,” in INTER-NOISE and NOISE-CON Congress and Conference Proceedings (Institute of Noise Control Engineering, 2021), Vol. 3.

Styles APA, Harvard, Vancouver, ISO, etc.

20

Yuan, Hao, Lei Cai, Zhengyang Wang, Xia Hu, Shaoting Zhang et Shuiwang Ji. « Computational modeling of cellular structures using conditional deep generative networks ». Bioinformatics 35, n^o 12 (6 novembre 2018) : 2141–49. http://dx.doi.org/10.1093/bioinformatics/bty923.

Texte intégral

Résumé :

Abstract Motivation Cellular function is closely related to the localizations of its sub-structures. It is, however, challenging to experimentally label all sub-cellular structures simultaneously in the same cell. This raises the need of building a computational model to learn the relationships among these sub-cellular structures and use reference structures to infer the localizations of other structures. Results We formulate such a task as a conditional image generation problem and propose to use conditional generative adversarial networks for tackling it. We employ an encoder–decoder network as the generator and propose to use skip connections between the encoder and decoder to provide spatial information to the decoder. To incorporate the conditional information in a variety of different ways, we develop three different types of skip connections, known as the self-gated connection, encoder-gated connection and label-gated connection. The proposed skip connections are built based on the conditional information using gating mechanisms. By learning a gating function, the network is able to control what information should be passed through the skip connections from the encoder to the decoder. Since the gate parameters are also learned automatically, we expect that only useful spatial information is transmitted to the decoder to help image generation. We perform both qualitative and quantitative evaluations to assess the effectiveness of our proposed approaches. Experimental results show that our cGAN-based approaches have the ability to generate the desired sub-cellular structures correctly. Our results also demonstrate that the proposed approaches outperform the existing approach based on adversarial auto-encoders, and the new skip connections lead to improved performance. In addition, the localizations of generated sub-cellular structures by our approaches are consistent with observations in biological experiments. Availability and implementation The source code and more results are available at https://github.com/divelab/cgan/.

Styles APA, Harvard, Vancouver, ISO, etc.

21

Li, Shuai, et Hongjun Li. « Deep Generative Modeling Based on VAE-GAN for 3D Indoor Scene Synthesis ». International Journal of Computer Games Technology 2023 (20 septembre 2023) : 1–11. http://dx.doi.org/10.1155/2023/3368647.

Texte intégral

Résumé :

With the advancement of virtual reality and 3D game technology, the demand for high-quality 3D indoor scene generation has surged. Addressing this need, this paper presents a method leveraging a VAE-GAN-based framework to conquer two primary challenges in 3D scene representation and deep generative networks. First, we introduce a matrix representation to encode fine-grained object attributes, alongside a complete graph to implicitly capture object spatial relations—effectively encapsulating both local and global scene structures. Second, we devise a unique generative framework based on VAE-GAN and the Bayesian optimization. This framework learns a Gaussian distribution of encoded object attributes through a VAE-GAN network, allowing for sampling and decoding of the distribution to generate new object attributes. Subsequently, a U-Net is employed to learn spatial relations between objects. Lastly, the Bayesian optimization module amalgamates the generated object attributes, spatial relations, and priors learned from data, conducting global optimization to generate a logical scene layout. Experimental results on a large-scale 3D indoor scene dataset substantiate that our method effectively learns inter-object relations and generates diverse and plausible indoor scenes. Comparative experiments and user studies further validate that our method surpasses the current state-of-the-art techniques in indoor scene generation and is comparable to real training scenes.

Styles APA, Harvard, Vancouver, ISO, etc.

22

Borysov, Stanislav S., Jeppe Rich et Francisco C. Pereira. « How to generate micro-agents ? A deep generative modeling approach to population synthesis ». Transportation Research Part C : Emerging Technologies 106 (septembre 2019) : 73–97. http://dx.doi.org/10.1016/j.trc.2019.07.006.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

23

Faez, Faezeh, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah et Hamid R. Rabiee. « SCGG : A deep structure-conditioned graph generative model ». PLOS ONE 17, n^o 11 (21 novembre 2022) : e0277887. http://dx.doi.org/10.1371/journal.pone.0277887.

Texte intégral

Résumé :

Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems. Making these methods able to consider different conditions during the generation procedure even increases their effectiveness by empowering them to generate new graph samples that meet the desired criteria. This paper presents a conditional deep graph generation method called SCGG that considers a particular type of structural conditions. Specifically, our proposed SCGG model takes an initial subgraph and autoregressively generates new nodes and their corresponding edges on top of the given conditioning substructure. The architecture of SCGG consists of a graph representation learning network and an autoregressive generative model, which is trained end-to-end. More precisely, the graph representation learning network is designed to compute continuous representations for each node in a graph, which are not only affected by the features of adjacent nodes, but also by the ones of farther nodes. This network is primarily responsible for providing the generation procedure with the structural condition, while the autoregressive generative model mainly maintains the generation history. Using this model, we can address graph completion, a rampant and inherently difficult problem of recovering missing nodes and their associated edges of partially observed graphs. The computational complexity of the SCGG method is shown to be linear in the number of graph nodes. Experimental results on both synthetic and real-world datasets demonstrate the superiority of our method compared with state-of-the-art baselines.

Styles APA, Harvard, Vancouver, ISO, etc.

24

Johnsen, Martin, Oliver Brandt, Sergio Garrido et Francisco Pereira. « Population synthesis for urban resident modeling using deep generative models ». Neural Computing and Applications 34, n^o 6 (3 novembre 2021) : 4677–92. http://dx.doi.org/10.1007/s00521-021-06622-2.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

25

Borsoi, Ricardo Augusto, Tales Imbiriba et Jose Carlos Moreira Bermudez. « Deep Generative Endmember Modeling : An Application to Unsupervised Spectral Unmixing ». IEEE Transactions on Computational Imaging 6 (2020) : 374–84. http://dx.doi.org/10.1109/tci.2019.2948726.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

26

Zhang, Qing, Benqiang Wang, Xusheng Liang, Yizhen Li, Feng He et Yuexiang Hao. « Digital Core Modeling Based on Pretrained Generative Adversarial Neural Networks ». Geofluids 2022 (5 septembre 2022) : 1–10. http://dx.doi.org/10.1155/2022/9159242.

Texte intégral

Résumé :

Accurately establishing a 3D digital core model is of great significance in oil and gas production. The physical experiment method and numerical modeling method are common modeling methods. With the development of deep learning technology, a variety of deep learning algorithms have been applied to digital core modeling. The digital core modeling method based on generative adversarial neural networks (GANs) has attracted wide attention due to its good quality and simple generation process. The disadvantage of this method is that the network needs thousands of trainings to achieve acceptable results. For this reason, this paper proposes to use the pretrained GANs for digital core modeling training, which can greatly reduce the number of network training while ensuring the core modeling effect. We can use the presented method to quickly complete the training and use the trained generator model to obtain multiple digital cores. By analyzing the quality of the generated cores from multiple aspects, it is revealed that the properties of the generated cores are in good agreement with the ones of the real core samples. The results indicate the reliability of the pretrained GAN method.

Styles APA, Harvard, Vancouver, ISO, etc.

27

Bucher, Martin Juan José, Michael Anton Kraus, Romana Rust et Siyu Tang. « Performance-Based Generative Design for Parametric Modeling of Engineering Structures Using Deep Conditional Generative Models ». Automation in Construction 156 (décembre 2023) : 105128. http://dx.doi.org/10.1016/j.autcon.2023.105128.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

28

Mishra, Akshansh, et Tarushi Pathak. « Deep Convolutional Generative Modeling for Artificial Microstructure Development of Aluminum-Silicon Alloy ». Indian Journal of Data Mining 1, n^o 1 (10 mai 2021) : 1–6. http://dx.doi.org/10.35940/ijdm.a1603.051121.

Texte intégral

Résumé :

Machine learning which is a sub-domain of an Artificial Intelligence which is finding various applications in manufacturing and material science sectors. In the present study, Deep Generative Modeling which a type of unsupervised machine learning technique has been adapted for the constructing the artificial microstructure of Aluminium-Silicon alloy. Deep Generative Adversarial Networks has been used for developing the artificial microstructure of the given microstructure image dataset. The results obtained showed that the developed models had learnt to replicate the lining near the certain images of the microstructures.

Styles APA, Harvard, Vancouver, ISO, etc.

29

Mishra, Akshansh, et Tarushi Pathak. « Deep Convolutional Generative Modeling for Artificial Microstructure Development of Aluminum-Silicon Alloy ». Indian Journal of Data Mining 1, n^o 1 (10 mai 2021) : 1–6. http://dx.doi.org/10.54105/ijdm.a1603.051121.

Texte intégral

Résumé :

Machine learning which is a sub-domain of an Artificial Intelligence which is finding various applications in manufacturing and material science sectors. In the present study, Deep Generative Modeling which a type of unsupervised machine learning technique has been adapted for the constructing the artificial microstructure of Aluminium-Silicon alloy. Deep Generative Adversarial Networks has been used for developing the artificial microstructure of the given microstructure image dataset. The results obtained showed that the developed models had learnt to replicate the lining near the certain images of the microstructures.

Styles APA, Harvard, Vancouver, ISO, etc.

30

Eguchi, Raphael R., Christian A. Choe et Po-Ssu Huang. « Ig-VAE : Generative modeling of protein structure by direct 3D coordinate generation ». PLOS Computational Biology 18, n^o 6 (27 juin 2022) : e1010271. http://dx.doi.org/10.1371/journal.pcbi.1010271.

Texte intégral

Résumé :

While deep learning models have seen increasing applications in protein science, few have been implemented for protein backbone generation—an important task in structure-based problems such as active site and interface design. We present a new approach to building class-specific backbones, using a variational auto-encoder to directly generate the 3D coordinates of immunoglobulins. Our model is torsion- and distance-aware, learns a high-resolution embedding of the dataset, and generates novel, high-quality structures compatible with existing design tools. We show that the Ig-VAE can be used with Rosetta to create a computational model of a SARS-CoV2-RBD binder via latent space sampling. We further demonstrate that the model’s generative prior is a powerful tool for guiding computational protein design, motivating a new paradigm under which backbone design is solved as constrained optimization problem in the latent space of a generative model.

Styles APA, Harvard, Vancouver, ISO, etc.

31

Bianco, Michael J., Sharon Gannot, Efren Fernandez-Grande et Peter Gerstoft. « Semi-Supervised Source Localization in Reverberant Environments With Deep Generative Modeling ». IEEE Access 9 (2021) : 84956–70. http://dx.doi.org/10.1109/access.2021.3087697.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

32

Bianco, Michael J., Sharon Gannot, Efren Fernandez-Grande et Peter Gerstoft. « Semi-supervised source localization in reverberant environments using deep generative modeling ». Journal of the Acoustical Society of America 148, n^o 4 (octobre 2020) : 2662. http://dx.doi.org/10.1121/1.5147419.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

33

Pham, Tuan Minh, et Xiangyang Ju. « Simulation of Hadronic Interactions with Deep Generative Models ». EPJ Web of Conferences 295 (2024) : 09034. http://dx.doi.org/10.1051/epjconf/202429509034.

Texte intégral

Résumé :

Accurate simulation of detector responses to hadrons is paramount for all physics programs at the Large Hadron Collider (LHC). Central to this simulation is the modeling of hadronic interactions. Unfortunately, the absence of first-principle theoretical guidance has made this a formidable challenge. The state-of-the-art simulation tool, Geant4, currently relies on phenomenology-inspired parametric models. Each model is designed to simulate hadronic interactions within specific energy ranges and for particular types of hadrons. Despite dedicated tuning efforts, these models sometimes fail to describe the data in certain physics processes accurately. Furthermore, finetuning these models with new measurements is laborious. Our research endeavors to leverage generative models to simulate hadronic interactions. While our ultimate goal is to train a generative model using experimental data, we have taken a crucial step by training conditional normalizing flow models with Geant4 simulation data. Our work marks a significant stride toward developing a fully differentiable and data-driven model for hadronic interactions in High Energy and Nuclear Physics.

Styles APA, Harvard, Vancouver, ISO, etc.

34

Yoshimori, Atsushi, Filip Miljković et Jürgen Bajorath. « Approach for the Design of Covalent Protein Kinase Inhibitors via Focused Deep Generative Modeling ». Molecules 27, n^o 2 (17 janvier 2022) : 570. http://dx.doi.org/10.3390/molecules27020570.

Texte intégral

Résumé :

Deep machine learning is expanding the conceptual framework and capacity of computational compound design, enabling new applications through generative modeling. We have explored the systematic design of covalent protein kinase inhibitors by learning from kinome-relevant chemical space, followed by focusing on an exemplary kinase of interest. Covalent inhibitors experience a renaissance in drug discovery, especially for targeting protein kinases. However, computational design of this class of inhibitors has thus far only been little investigated. To this end, we have devised a computational approach combining fragment-based design and deep generative modeling augmented by three-dimensional pharmacophore screening. This approach is thought to be particularly relevant for medicinal chemistry applications because it combines knowledge-based elements with deep learning and is chemically intuitive. As an exemplary application, we report for Bruton’s tyrosine kinase (BTK), a major drug target for the treatment of inflammatory diseases and leukemia, the generation of novel candidate inhibitors with a specific chemically reactive group for covalent modification, requiring only little target-specific compound information to guide the design efforts. Newly generated compounds include known inhibitors and characteristic substructures and many novel candidates, thus lending credence to the computational approach, which is readily applicable to other targets.

Styles APA, Harvard, Vancouver, ISO, etc.

35

Mizginov, V. A., et S. Y. Danilov. « SYNTHETIC THERMAL BACKGROUND AND OBJECT TEXTURE GENERATION USING GEOMETRIC INFORMATION AND GAN ». ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2/W12 (9 mai 2019) : 149–54. http://dx.doi.org/10.5194/isprs-archives-xlii-2-w12-149-2019.

Texte intégral

Résumé :

<p><strong>Abstract.</strong> Nowadays methods based on deep neural networks show the best performance among image recognition and object detection algorithms. Nevertheless, such methods require to have large databases of multispectral images of various objects to achieve state-of-the-art results. Therefore the dataset generation is one of the major challenges for the successful training of a deep neural network. However, infrared image datasets that are large enough for successful training of a deep neural network are not available in the public domain. Generation of synthetic datasets using 3D models of various scenes is a time-consuming method that requires long computation time and is not very realistic. This paper is focused on the development of the method for thermal image synthesis using a GAN (generative adversarial network). The aim of the presented work is to expand and complement the existing datasets of real thermal images. Today, deep convolutional networks are increasingly used for the goal of synthesizing various images. Recently a new generation of such algorithms commonly called GAN has become a promising tool for synthesizing images of various spectral ranges. These networks show effective results for image-to-image translations. While it is possible to generate a thermal texture for a single object, generation of environment textures is extremely difficult due to the presence of a large number of objects with different emission sources. The proposed method is based on a joint approach that uses 3D modeling and deep learning. Synthesis of background textures and objects textures is performed using a generative-adversarial neural network and semantic and geometric information about objects generated using 3D modeling. The developed approach significantly improves the realism of the synthetic images, especially in terms of the quality of background textures.</p>

Styles APA, Harvard, Vancouver, ISO, etc.

36

Lim, Jieon, et Weonyoung Joo. « Counterfactual image generation by disentangling data attributes with deep generative models ». Communications for Statistical Applications and Methods 30, n^o 6 (30 novembre 2023) : 589–603. http://dx.doi.org/10.29220/csam.2023.30.6.589.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

37

Saito, Yuki, Shinnosuke Takamichi et Hiroshi Saruwatari. « Perceptual-Similarity-Aware Deep Speaker Representation Learning for Multi-Speaker Generative Modeling ». IEEE/ACM Transactions on Audio, Speech, and Language Processing 29 (2021) : 1033–48. http://dx.doi.org/10.1109/taslp.2021.3059114.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

38

Zhang, Jincheng, et Xiaowei Zhao. « Wind farm wake modeling based on deep convolutional conditional generative adversarial network ». Energy 238 (janvier 2022) : 121747. http://dx.doi.org/10.1016/j.energy.2021.121747.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

39

Wang, Liwei, Yu-Chin Chan, Faez Ahmed, Zhao Liu, Ping Zhu et Wei Chen. « Deep generative modeling for mechanistic-based learning and design of metamaterial systems ». Computer Methods in Applied Mechanics and Engineering 372 (décembre 2020) : 113377. http://dx.doi.org/10.1016/j.cma.2020.113377.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

40

Mujahid, Omer, Ivan Contreras, Aleix Beneyto, Ignacio Conget, Marga Giménez et Josep Vehi. « Conditional Synthesis of Blood Glucose Profiles for T1D Patients Using Deep Generative Models ». Mathematics 10, n^o 20 (12 octobre 2022) : 3741. http://dx.doi.org/10.3390/math10203741.

Texte intégral

Résumé :

Mathematical modeling of the glucose–insulin system forms the core of simulators in the field of glucose metabolism. The complexity of human biological systems makes it a challenging task for the physiological models to encompass the entirety of such systems. Even though modern diabetes simulators perform a respectable task of simulating the glucose–insulin action, they are unable to estimate various phenomena affecting the glycemic profile of an individual such as glycemic disturbances and patient behavior. This research work presents a potential solution to this problem by proposing a method for the generation of blood glucose values conditioned on plasma insulin approximation of type 1 diabetes patients using a pixel-to-pixel generative adversarial network. Two type-1 diabetes cohorts comprising 29 and 6 patients, respectively, are used to train the generative model. This study shows that the generated blood glucose values are statistically similar to the real blood glucose values, mimicking the time-in-range results for each of the standard blood glucose ranges in type 1 diabetes management and obtaining similar means and variability outcomes. Furthermore, the causal relationship between the plasma insulin values and the generated blood glucose conforms to the same relationship observed in real patients. These results herald the aptness of deep generative models for the generation of virtual patients with diabetes.

Styles APA, Harvard, Vancouver, ISO, etc.

41

Zervou, Michaela, Effrosyni Doutsi, Yannis Pantazis et Panagiotis Tsakalides. « De Novo Antimicrobial Peptide Design with Feedback Generative Adversarial Networks ». International Journal of Molecular Sciences 25, n^o 10 (18 mai 2024) : 5506. http://dx.doi.org/10.3390/ijms25105506.

Texte intégral

Résumé :

Antimicrobial peptides (AMPs) are promising candidates for new antibiotics due to their broad-spectrum activity against pathogens and reduced susceptibility to resistance development. Deep-learning techniques, such as deep generative models, offer a promising avenue to expedite the discovery and optimization of AMPs. A remarkable example is the Feedback Generative Adversarial Network (FBGAN), a deep generative model that incorporates a classifier during its training phase. Our study aims to explore the impact of enhanced classifiers on the generative capabilities of FBGAN. To this end, we introduce two alternative classifiers for the FBGAN framework, both surpassing the accuracy of the original classifier. The first classifier utilizes the k-mers technique, while the second applies transfer learning from the large protein language model Evolutionary Scale Modeling 2 (ESM2). Integrating these classifiers into FBGAN not only yields notable performance enhancements compared to the original FBGAN but also enables the proposed generative models to achieve comparable or even superior performance to established methods such as AMPGAN and HydrAMP. This achievement underscores the effectiveness of leveraging advanced classifiers within the FBGAN framework, enhancing its computational robustness for AMP de novo design and making it comparable to existing literature.

Styles APA, Harvard, Vancouver, ISO, etc.

42

Donovan-Maiye, Rory M., Jackson M. Brown, Caleb K. Chan, Liya Ding, Calysta Yan, Nathalie Gaudreault, Julie A. Theriot, Mary M. Maleckar, Theo A. Knijnenburg et Gregory R. Johnson. « A deep generative model of 3D single-cell organization ». PLOS Computational Biology 18, n^o 1 (18 janvier 2022) : e1009155. http://dx.doi.org/10.1371/journal.pcbi.1009155.

Texte intégral

Résumé :

We introduce a framework for end-to-end integrative modeling of 3D single-cell multi-channel fluorescent image data of diverse subcellular structures. We employ stacked conditional β-variational autoencoders to first learn a latent representation of cell morphology, and then learn a latent representation of subcellular structure localization which is conditioned on the learned cell morphology. Our model is flexible and can be trained on images of arbitrary subcellular structures and at varying degrees of sparsity and reconstruction fidelity. We train our full model on 3D cell image data and explore design trade-offs in the 2D setting. Once trained, our model can be used to predict plausible locations of structures in cells where these structures were not imaged. The trained model can also be used to quantify the variation in the location of subcellular structures by generating plausible instantiations of each structure in arbitrary cell geometries. We apply our trained model to a small drug perturbation screen to demonstrate its applicability to new data. We show how the latent representations of drugged cells differ from unperturbed cells as expected by on-target effects of the drugs.

Styles APA, Harvard, Vancouver, ISO, etc.

43

Richie, Rodney C. « Basics of Artificial Intelligence (AI) Modeling ». Journal of Insurance Medicine 51, n^o 1 (28 mai 2024) : 35–40. http://dx.doi.org/10.17849/insm-51-1-35-40.1.

Texte intégral

Résumé :

AI with machine learning and its subset deep learning are revolutionizing research into the morbidity and mortality of diseases and conditions. The major models of AI are discussed, with an attempt to simplify what many acknowledge as agnostic processing of vast amounts of data to arrive at a conclusion or diagnosis. Such models include convolutional neural networks, artificial neural networks, recurrent neural networks, generative adversarial networks, local interpretable model-agnostic explanations, shapley additive explanations, counterfactual explanations, multi-armed bandit models, deep-Q-learning models, fusion models, federated learning, predictive modeling, and disease outbreak prediction. Topics are well-referenced for further research. Methodology A key-word search of artificial intelligence, artificial intelligence in medicine, and artificial intelligence models was done in PubMed and Google Scholar yielded more than 100 articles that were reviewed for summation in this article.

Styles APA, Harvard, Vancouver, ISO, etc.

44

Ruan, Xiongtao, et Robert F. Murphy. « Evaluation of methods for generative modeling of cell and nuclear shape ». Bioinformatics 35, n^o 14 (7 décembre 2018) : 2475–85. http://dx.doi.org/10.1093/bioinformatics/bty983.

Texte intégral

Résumé :

Abstract Motivation Cell shape provides both geometry for, and a reflection of, cell function. Numerous methods for describing and modeling cell shape have been described, but previous evaluation of these methods in terms of the accuracy of generative models has been limited. Results Here we compare traditional methods and deep autoencoders to build generative models for cell shapes in terms of the accuracy with which shapes can be reconstructed from models. We evaluated the methods on different collections of 2D and 3D cell images, and found that none of the methods gave accurate reconstructions using low dimensional encodings. As expected, much higher accuracies were observed using high dimensional encodings, with outline-based methods significantly outperforming image-based autoencoders. The latter tended to encode all cells as having smooth shapes, even for high dimensions. For complex 3D cell shapes, we developed a significant improvement of a method based on the spherical harmonic transform that performs significantly better than other methods. We obtained similar results for the joint modeling of cell and nuclear shape. Finally, we evaluated the modeling of shape dynamics by interpolation in the shape space. We found that our modified method provided lower deformation energies along linear interpolation paths than other methods. This allows practical shape evolution in high dimensional shape spaces. We conclude that our improved spherical harmonic based methods are preferable for cell and nuclear shape modeling, providing better representations, higher computational efficiency and requiring fewer training images than deep learning methods. Availability and implementation All software and data is available at http://murphylab.cbd.cmu.edu/software. Supplementary information Supplementary data are available at Bioinformatics online.

Styles APA, Harvard, Vancouver, ISO, etc.

45

Xu, Yanwu, Mingming Gong, Junxiang Chen, Tongliang Liu, Kun Zhang et Kayhan Batmanghelich. « Generative-Discriminative Complementary Learning ». Proceedings of the AAAI Conference on Artificial Intelligence 34, n^o 04 (3 avril 2020) : 6526–33. http://dx.doi.org/10.1609/aaai.v34i04.6126.

Texte intégral

Résumé :

The majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminative complementary learning method that estimates the ordinary labels by modeling both the conditional (discriminative) and instance (generative) distributions. Our method, we call Complementary Conditional GAN (CCGAN), improves the accuracy of predicting ordinary labels and is able to generate high-quality instances in spite of weak supervision. In addition to the extensive empirical studies, we also theoretically show that our model can retrieve the true conditional distribution from the complementarily-labeled data.

Styles APA, Harvard, Vancouver, ISO, etc.

46

Hou, Wenshu, Zicheng Liu, Junjie Deng et Jiacheng Wang. « How does AI create and recommend corresponding wallpapers based on the games played by users ? » Applied and Computational Engineering 42, n^o 1 (23 février 2024) : 147–55. http://dx.doi.org/10.54254/2755-2721/42/20230770.

Texte intégral

Résumé :

The purpose of this paper is to give a comprehensive review of the related work that has everything to do with creating a wallpaper in artificial intelligence (AI) technology. Firstly, deep learning and neural network are summarized, especially generative adversarial networks that aim to effective generate images. Then, User interest modeling is summarized and analyzed, which is a key point to figure out the preference of the players. Further, main ideas are given about the trends and directions of wallpaper generation by AI.

Styles APA, Harvard, Vancouver, ISO, etc.

47

Shchetinin, Eugeny Yu. « Brain-computer interaction modeling based on the stable diffusion model ». Discrete and Continuous Models and Applied Computational Science 31, n^o 3 (12 septembre 2023) : 273–81. http://dx.doi.org/10.22363/2658-4670-2023-31-3-273-281.

Texte intégral

Résumé :

This paper investigates neurotechnologies for developing brain-computer interaction (BCI) based on the generative deep learning Stable Diffusion model. An algorithm for modeling BCI is proposed and its training and testing on artificial data is described. The results are encouraging researchers and can be used in various areas of BCI, such as distance learning, remote medicine and the creation of robotic humanoids, etc.

Styles APA, Harvard, Vancouver, ISO, etc.

48

Feldkamp, Niclas, Soeren Bergmann, Florian Conrad et Steffen Strassburger. « A Method Using Generative Adversarial Networks for Robustness Optimization ». ACM Transactions on Modeling and Computer Simulation 32, n^o 2 (30 avril 2022) : 1–22. http://dx.doi.org/10.1145/3503511.

Texte intégral

Résumé :

The evaluation of robustness is an important goal within simulation-based analysis, especially in production and logistics systems. Robustness refers to setting controllable factors of a system in such a way that variance in the uncontrollable factors (noise) has minimal effect on a given output. In this paper, we present an approach for optimizing robustness based on deep generative models, a special method of deep learning. We propose a method consisting of two Generative Adversarial Networks (GANs) to generate optimized experiment plans for the decision factors and the noise factors in a competitive, turn-based game. In a case study, the proposed method is tested and compared to traditional methods for robustness analysis including Taguchi method and Response Surface Method.

Styles APA, Harvard, Vancouver, ISO, etc.

49

Srikanth, M., et Bhanurangarao M. « Deep Learning Approaches for Predictive Modeling and Optimization of Metabolic Fluxes in Engineered Microorganism ». Aug-Sept 2023, n^o 35 (21 juillet 2023) : 1–11. http://dx.doi.org/10.55529/ijrise.35.1.11.

Texte intégral

Résumé :

Deep learning approaches have emerged as powerful tools for predictive modeling and optimization of metabolic fluxes in engineered microorganisms. These approaches leverage the capabilities of deep neural networks to capture complex patterns and relationships in large-scale biological datasets. This paper provides an overview of the deep learning techniques commonly employed in this field, including Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Reinforcement Learning (RL), and Transfer Learning. Each approach is briefly described, highlighting its potential applications in predicting and optimizing metabolic fluxes. The importance of data preprocessing, model architecture selection, and optimization techniques is also emphasized. The promising results obtained from these deep learning approaches suggest their potential to enhance metabolic engineering strategies and facilitate the design of more efficient and sustainable bioprocesses.

Styles APA, Harvard, Vancouver, ISO, etc.

50

Varga, Michal, Ján Jadlovský et Slávka Jadlovská. « Generative Enhancement of 3D Image Classifiers ». Applied Sciences 10, n^o 21 (22 octobre 2020) : 7433. http://dx.doi.org/10.3390/app10217433.

Texte intégral

Résumé :

In this paper, we propose a methodology for generative enhancement of existing 3D image classifiers. This methodology is based on combining the advantages of both non-generative classifiers and generative modeling. Its purpose is to streamline the synthesis of novel deep neural networks by embedding existing compatible classifiers into a generative network architecture. A demonstration of this process and evaluation of its effectiveness is performed using a 3D convolutional classifier and its generative equivalent—a 3D conditional generative adversarial network classifier. The results of the experiments show that the generative classifier delivers higher performance, gaining a relative classification accuracy improvement of 7.43%. An increase of accuracy is also observed when comparing it to a plain convolutional classifier that was trained on a dataset augmented with samples created by the trained generator. This suggests a desirable knowledge sharing mechanism exists within the hybrid discriminator-classifier network.

Styles APA, Harvard, Vancouver, ISO, etc.

Articles de revues sur le sujet « Deep generative modeling »

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres