Journal articles: 'Generative approach'

1

Victor Parque, Masakazu Kobayashi, and Masatake Higashi. "3105 A Generative Approach to Wire Harness Design." Proceedings of Design & Systems Conference 2013.23 (2013): _3105–1_—_3105–2_. http://dx.doi.org/10.1299/jsmedsd.2013.23._3105-1_.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Soddu, Celestino. "New Naturality: A Generative Approach to Art and Design." Leonardo 35, no. 3 (June 2002): 291–94. http://dx.doi.org/10.1162/002409402760105299.

Full text

Abstract:

In the field of generative art and design, design concepts are represented as code. This generative code functions as DNA does in nature. It uses artificial life to generate a multiplicity of possible artworks, artificial events, architectures and virtual environments. In the generative approach the real artwork is not merely a product, such as an image or 3D model. The generative artwork is an Idea-Product. It represents an artificial species able to generate an endless sequence of individual events, each one different, unique and unrepeatable but belonging to the same identifiable design Idea. The author's project, Argenia, realizes the “new naturality” of artificial objects.

APA, Harvard, Vancouver, ISO, and other styles

3

Wong, Alexander, Mohammad Javad Shafiee, Brendan Chwyl, and Francis Li. "GenSynth: a generative synthesis approach to learning generative machines for generate efficient neural networks." Electronics Letters 55, no. 18 (September 2019): 986–89. http://dx.doi.org/10.1049/el.2019.1719.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Ye, Hongbin, Ningyu Zhang, Shumin Deng, Mosha Chen, Chuanqi Tan, Fei Huang, and Huajun Chen. "Contrastive Triple Extraction with Generative Transformer." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 16 (May 18, 2021): 14257–65. http://dx.doi.org/10.1609/aaai.v35i16.17677.

Full text

Abstract:

Triple extraction is an essential task in information extraction for natural language processing and knowledge graph construction. In this paper, we revisit the end-to-end triple extraction task for sequence generation. Since generative triple extraction may struggle to capture long-term dependencies and generate unfaithful triples, we introduce a novel model, contrastive triple extraction with a generative transformer. Specifically, we introduce a single shared transformer module for encoder-decoder-based generation. To generate faithful results, we propose a novel triplet contrastive training object. Moreover, we introduce two mechanisms to further improve model performance (i.e., batch-wise dynamic attention-masking and triple-wise calibration). Experimental results on three datasets (i.e., NYT, WebNLG, and MIE) show that our approach achieves better performance than that of baselines.

APA, Harvard, Vancouver, ISO, and other styles

5

Čučaković, Aleksandar, Biljana Jović, and Mirjana Komnenov. "Biomimetic Geometry Approach to Generative Design." Periodica Polytechnica Architecture 47, no. 2 (2016): 70–74. http://dx.doi.org/10.3311/ppar.10082.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Jager, Gottfried. "Generative Photography: A Systematic, Constructive Approach." Leonardo 19, no. 1 (1986): 19. http://dx.doi.org/10.2307/1578296.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Ren, Yong, Yucen Luo, and Jun Zhu. "Improving Generative Moment Matching Networks with Distribution Partition." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 11 (May 18, 2021): 9403–10. http://dx.doi.org/10.1609/aaai.v35i11.17133.

Full text

Abstract:

Generative moment matching networks (GMMN) present a theoretically sound approach to learning deep generative mod-els. However, such methods are typically limited by the high sample complexity, thereby impractical in generating complex data. In this paper, we present a new strategy to train GMMN with a low sample complexity while retaining the theoretical soundness. Our method introduces some auxiliary variables, whose values are provided by a pre-trained model such as an encoder network in practice. Conditioned on these variables, we partition the distribution into a set of conditional distributions, which can be effectively matched with a low sample complexity. We instantiate this strategy by presenting an amortized network called GMMN-DP with shared auxiliary variable information for the data generation task, as well as developing an efficient stochastic training algorithm.The experimental results show that GMMN-DP can generate complex samples on datasets such as CelebA and CIFAR-10, where the vanilla GMMN fails.

APA, Harvard, Vancouver, ISO, and other styles

8

Coorey, Benjamin P., and Julie R. Jupp. "Generative spatial performance design system." Artificial Intelligence for Engineering Design, Analysis and Manufacturing 28, no. 3 (July 22, 2014): 277–83. http://dx.doi.org/10.1017/s0890060414000225.

Full text

Abstract:

AbstractArchitectural spatial design is a wicked problem that can have a multitude of solutions for any given brief. The information needed to resolve architectural design problems is often not readily available during the early conceptual stages, requiring proposals to be evaluated only after an initial solution is reached. This “solution-driven” design approach focuses on the generation of designs as a means to explore the solution space. Generative design can be achieved computationally through parametric and algorithmic processes. However, utilizing a large repertoire of organiational patterns and design precedent knowledge together with the precise criteria of spatial evaluation can present design challenges even to an experienced architect. In the implementation of a parametric design process lies an opportunity to supplement the designer's knowledge with computational decision support that provides real-time spatial feedback during conceptual design. This paper presents an approach based on a generative multiperformance framework, configured for generating and optimizing architectural designs based on a precedent design. The system is constructed using a parametric modeling environment enabling the capture of precedent designs, extraction of spatial analytics, and demonstration of how populations can be used to drive the generation and optimization of alternate spatial solutions. A pilot study implementing the complete workflow of the system is used to illustrate the benefits of coupling parametric modeling with structured precedent analysis and design generation.

APA, Harvard, Vancouver, ISO, and other styles

9

Arunkumar, A., A. Sooriyamoorthy, C. Mishael, and A. Giri. "A study on engine piston optimization by generative design approach." IOP Conference Series: Materials Science and Engineering 1228, no. 1 (March 1, 2022): 012014. http://dx.doi.org/10.1088/1757-899x/1228/1/012014.

Full text

Abstract:

Abstract Significant enterprises today favor the cooperation of generative plans in the manufacturing and assembling departments. Therefore our aim is to dwell on the more straightforward degrees of generative design to demonstrate the modification of boundary conditions and properties to exhibit modern applications. Generative Design has demonstrated to be a significant upgrade in the machine-producing side of the business because of the simplicity in changes, higher resilience, and reduced number of faults that arise. Nevertheless owing to the added complex shape of structures, the model generation and design are posed with challenges. This paper involves the examination and generative design of a 4-Stroke engine piston. The proposed method is validated through a study which closely resembles a real life prototype. The examination aims to dissect and detail a newly formed design grid for the current cylinder of the F20C 4 - stroke 4 - cylinder engine at the core of the Honda S2000. Our aim to study on piston design, which makes it lighter and more efficient while keeping the similar volume yield in the cylinder. The paper depicts the process of optimizing the component through mass reduction where the mass was reduced by close to twenty three percent.

APA, Harvard, Vancouver, ISO, and other styles

10

Joshi, Ameya, Minsu Cho, Viraj Shah, Balaji Pokuri, Soumik Sarkar, Baskar Ganapathysubramanian, and Chinmay Hegde. "InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 4377–84. http://dx.doi.org/10.1609/aaai.v34i04.5863.

Full text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

11

Vranic, Valentino, and Roman Táborský. "Features as transformations: A generative approach to software development." Computer Science and Information Systems 13, no. 3 (2016): 759–78. http://dx.doi.org/10.2298/csis160128027v.

Full text

Abstract:

The objective of feature modeling is to foster software reuse by enabling to explicitly and abstractly express commonality and variability in the domain. Feature modeling is used to configure other models and, eventually, code. These software assets are being configured by the feature model based on the selection of variable features. However, selecting a feature is far from a naive component based approach where feature inclusion would simply mean including the corresponding component. More often than not, feature inclusion affects several places in models or code to be configured requiring their nontrivial adaptation. Thus, feature inclusion recalls transformation and this is at heart of the approach to feature model driven generation of software artifacts proposed in this paper. Features are viewed as transformations that may be executed during the generative process conducted by the feature model configuration. The generative process is distributed in respective transformations enabling the developers to have a better control over it. This approach can be applied to modularize changes in product customization and to establish generative software product lines by gradual refactoring of existing products.

APA, Harvard, Vancouver, ISO, and other styles

12

Blaschke, Thomas, and Jürgen Bajorath. "Compound dataset and custom code for deep generative multi-target compound design." Future Science OA 7, no. 6 (July 2021): FSO715. http://dx.doi.org/10.2144/fsoa-2021-0033.

Full text

Abstract:

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.

APA, Harvard, Vancouver, ISO, and other styles

13

Mountstephens, James, and Jason Teo. "Progress and Challenges in Generative Product Design: A Review of Systems." Computers 9, no. 4 (October 9, 2020): 80. http://dx.doi.org/10.3390/computers9040080.

Full text

Abstract:

Design is a challenging task that is crucial to all product development. Advances in design computing may allow machines to move from a supporting role to generators of design content. Generative Design systems produce designs by algorithms and offer the potential for the exploration of vast design spaces, the fostering of creativity, the combination of objective and subjective requirements, and the revolutionary integration of conceptual and detailed design phases. The application of generative methods to the design of discrete, physical, engineered products has not yet been reviewed. This paper reviews the Generative Product Design systems developed since 1998 in order to identify significant approaches and trends. Systems are analyzed according to their primary goal, generative method, the design phase they focus on, whether the generation is automatic or interactive, the number of design options they generate, and the types of design requirements involved in the generation process. Progress using this approach is recognized, and a number of challenges that must be addressed in order to achieve widespread acceptance are identified. Possible solutions are offered, including innovative approaches in Human–Computer Interaction.

APA, Harvard, Vancouver, ISO, and other styles

14

Li, Haibing, and Roland Lachmayer. "Generative Design Approach for Modeling Creative Designs." IOP Conference Series: Materials Science and Engineering 408 (October 1, 2018): 012035. http://dx.doi.org/10.1088/1757-899x/408/1/012035.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Shi, Weili. "A Generative Approach to Chinese Shanshui Painting." IEEE Computer Graphics and Applications 37, no. 1 (January 2017): 15–19. http://dx.doi.org/10.1109/mcg.2017.13.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Chen, Changlu, Chaoxi Niu, Xia Zhan, and Kun Zhan. "Generative approach to unsupervised deep local learning." Journal of Electronic Imaging 28, no. 04 (July 10, 2019): 1. http://dx.doi.org/10.1117/1.jei.28.4.043005.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Desolneux, Agnès. "When the a contrario approach becomes generative." International Journal of Computer Vision 116, no. 1 (April 16, 2015): 46–65. http://dx.doi.org/10.1007/s11263-015-0825-x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Liu, Hong, and Yan Li. "Generative design supported by evolutionary computing approach." International Journal of Computer Applications in Technology 30, no. 1/2 (2007): 69. http://dx.doi.org/10.1504/ijcat.2007.015698.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Raghavan, S. V., D. Vasukiammaiyar, and Günter Haring. "Hierarchical approach to building generative networkload models." Computer Networks and ISDN Systems 27, no. 7 (May 1995): 1193–206. http://dx.doi.org/10.1016/0169-7552(94)00012-i.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Hinkelmann, Knut, and Dimitris Karagiannis. "Context-sensitive office tasks a generative approach." Decision Support Systems 8, no. 3 (June 1992): 255–67. http://dx.doi.org/10.1016/0167-9236(92)90018-k.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Li, Junyi, Xintong Wang, Yaoyang Lin, Arunesh Sinha, and Michael Wellman. "Generating Realistic Stock Market Order Streams." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 01 (April 3, 2020): 727–34. http://dx.doi.org/10.1609/aaai.v34i01.5415.

Full text

Abstract:

We propose an approach to generate realistic and high-fidelity stock market data based on generative adversarial networks (GANs). Our Stock-GAN model employs a conditional Wasserstein GAN to capture history dependence of orders. The generator design includes specially crafted aspects including components that approximate the market's auction mechanism, augmenting the order history with order-book constructions to improve the generation task. We perform an ablation study to verify the usefulness of aspects of our network structure. We provide a mathematical characterization of distribution learned by the generator. We also propose statistics to measure the quality of generated orders. We test our approach with synthetic and actual market data, compare to many baseline generative models, and find the generated data to be close to real data.

APA, Harvard, Vancouver, ISO, and other styles

22

Buncher, Brandon, Awshesh Nath Sharma, and Matias Carrasco Kind. "Survey2Survey: a deep learning generative model approach for cross-survey image mapping." Monthly Notices of the Royal Astronomical Society 503, no. 1 (February 3, 2021): 777–96. http://dx.doi.org/10.1093/mnras/stab294.

Full text

Abstract:

ABSTRACT During the last decade, there has been an explosive growth in survey data and deep learning techniques, both of which have enabled great advances for astronomy. The amount of data from various surveys from multiple epochs with a wide range of wavelengths, albeit with varying brightness and quality, is overwhelming, and leveraging information from overlapping observations from different surveys has limitless potential in understanding galaxy formation and evolution. Synthetic galaxy image generation using physical models has been an important tool for survey data analysis, while deep learning generative models show great promise. In this paper, we present a novel approach for robustly expanding and improving survey data through cross survey feature translation. We trained two types of neural networks to map images from the Sloan Digital Sky Survey (SDSS) to corresponding images from the Dark Energy Survey (DES). This map was used to generate false DES representations of SDSS images, increasing the brightness and S/N while retaining important morphological information. We substantiate the robustness of our method by generating DES representations of SDSS images from outside the overlapping region, showing that the brightness and quality are improved even when the source images are of lower quality than the training images. Finally, we highlight images in which the reconstruction process appears to have removed large artefacts from SDSS images. While only an initial application, our method shows promise as a method for robustly expanding and improving the quality of optical survey data and provides a potential avenue for cross-band reconstruction.

APA, Harvard, Vancouver, ISO, and other styles

23

Janssen, Patrick H. T., John H. Frazer, and Ming-Xi Tang. "A Framework for Generating and Evolving Building Designs." International Journal of Architectural Computing 3, no. 4 (December 2005): 449–70. http://dx.doi.org/10.1260/147807705777781112.

Full text

Abstract:

This paper describes a comprehensive framework for generative evolutionary design. The key problem that is identified is generating alternative designs with an appropriate level of variability. Within the proposed framework, the design process is split into two phases: in the first phase, the design team develops and encodes the essential and identifiable character of the designs to be generated and evolved; in the second phase, the design team uses an evolutionary system to generate and evolve designs that embody this character. This approach allows design variability to be carefully controlled. In order to verify the feasibility of the proposed framework, a generative process capable of generating controlled variability is implemented and demonstrated.

APA, Harvard, Vancouver, ISO, and other styles

24

Maarouf, Ibrahim ElSayed, and Sherif Usama Zeid. "PARAMETRIC APPROACH FOR GENERATING NEW MUQARNAS." Journal of Islamic Architecture 5, no. 3 (July 1, 2019): 111–18. http://dx.doi.org/10.18860/jia.v5i3.5322.

Full text

Abstract:

In recent decades, the search for new geometrical innovations has been of great interest for contemporary architects artists, trying to escape the repetitive use of historical ornamental details of architectural styles orders or the absence of such ornaments in the modern style. This paper aims to lay down the basis for generating new muqarnas elements based on the cosmological nature of Islamic Architecture, but still preserving its concepts. The muqarnas was chosen because it is one of most original inventions of Islamic architecture and one of its most effective and widespread applications. Innovation in its design requires freedom of expression that can be limited by design software. Furthermore, the process of testing ideas can be tedious and time-consuming. Parametric and generative design, using Grasshopper, is used to reformulate the muqarnas generation process using visual programming. Parametric design and hypothetical geometric patterns in a linear or polar arraying direction produce a clearly defined muqarnas.

APA, Harvard, Vancouver, ISO, and other styles

25

Tiancheng, Shi, De Gejirifu, Cong Hao, Guo Wenzhang, Zhong Yalin, and Qian Long. "Scenario Generation for Wind Power Using Generative Adversarial Networks." Journal of Physics: Conference Series 2320, no. 1 (August 1, 2022): 012019. http://dx.doi.org/10.1088/1742-6596/2320/1/012019.

Full text

Abstract:

Abstract Scenarios generation is a critical part in planning and operation in high renewable energy penetratied power systems. However, the statistical assumptions of traditional parametric methods may not hold for all types of wind farms. In this paper, a data-driven artificial intelligence approach is presented to generate wind power output scenarios based on generative adversarial networks (GANs). Unlike traditional probabilistic model-based techniques which are typically difficult to scale or sample, the proposed method is data-driven and captures patterns of wind power generation. First, the GAN network structure is constructed, and the Wasserstein distance is employed as the discriminator’s loss function. The GAN training then enables the generator to learn random noise and actual history data. Finally, the scenario generation approach based on Monte Carlo simulation and GANs are compared. It shows that the scenarios generated by proposed method can accurately describe the uncertainty of wind power output.

APA, Harvard, Vancouver, ISO, and other styles

26

Kumar, Dheeraj, Mayuri A. Mehta, and Indranath Chatterjee. "Empirical Analysis of Deep Convolutional Generative Adversarial Network for Ultrasound Image Synthesis." Open Biomedical Engineering Journal 15, no. 1 (October 18, 2021): 71–77. http://dx.doi.org/10.2174/1874120702115010071.

Full text

Abstract:

Introduction: Recent research on Generative Adversarial Networks (GANs) in the biomedical field has proven the effectiveness in generating synthetic images of different modalities. Ultrasound imaging is one of the primary imaging modalities for diagnosis in the medical domain. In this paper, we present an empirical analysis of the state-of-the-art Deep Convolutional Generative Adversarial Network (DCGAN) for generating synthetic ultrasound images. Aims: This work aims to explore the utilization of deep convolutional generative adversarial networks for the synthesis of ultrasound images and to leverage its capabilities. Background: Ultrasound imaging plays a vital role in healthcare for timely diagnosis and treatment. Increasing interest in automated medical image analysis for precise diagnosis has expanded the demand for a large number of ultrasound images. Generative adversarial networks have been proven beneficial for increasing the size of data by generating synthetic images. Objective: Our main purpose in generating synthetic ultrasound images is to produce a sufficient amount of ultrasound images with varying representations of a disease. Methods: DCGAN has been used to generate synthetic ultrasound images. It is trained on two ultrasound image datasets, namely, the common carotid artery dataset and nerve dataset, which are publicly available on Signal Processing Lab and Kaggle, respectively. Results: Results show that good quality synthetic ultrasound images are generated within 100 epochs of training of DCGAN. The quality of synthetic ultrasound images is evaluated using Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM). We have also presented some visual representations of the slices of generated images for qualitative comparison. Conclusion: Our empirical analysis reveals that synthetic ultrasound image generation using DCGAN is an efficient approach. Other: In future work, we plan to compare the quality of images generated through other adversarial methods such as conditional GAN, progressive GAN.

APA, Harvard, Vancouver, ISO, and other styles

27

Patarakin, Yevgeny D., and Boris B. Yarmakhov. "Data farming for virtual school laboratories." RUDN Journal of Informatization in Education 18, no. 4 (December 15, 2021): 347–59. http://dx.doi.org/10.22363/2312-8631-2021-18-4-347-359.

Full text

Abstract:

Problem and goal. Building statistical, mathematical, computational and research literacies in teaching school subjects is discussed in the article. The purpose is to develop a model for generating data for research experiments by students. Methodology. The Netlogo data generation and consecutive statistical data procession in CODAP and R programming language were used. Results. The generative approach helps students to work with data collected by agents, programmed by students themselves. In doing so, the student assumes the position of a researcher, who plans an experiment and analyses its results. Conclusion. The proposed approach of data generation and analysis allows to introduce the student to the contemporary culture of generating and sharing data.

APA, Harvard, Vancouver, ISO, and other styles

28

ECKERT, CLAUDIA, IAN KELLY, and MARTIN STACEY. "Interactive generative systems for conceptual design: An empirical perspective." Artificial Intelligence for Engineering Design, Analysis and Manufacturing 13, no. 4 (September 1999): 303–20. http://dx.doi.org/10.1017/s089006049913405x.

Full text

Abstract:

This paper argues from extensive research findings in design psychology and industrial design processes, as well as our own observations, that interactive generative systems can be powerful tools for human designers. Moreover, interactive generative systems can fit naturally into human design thinking and industrial design practice. This discussion is focused on aesthetic design fields like knitwear and graphic design, but is largely applicable to major branches of engineering. Human designers and generative systems have complementary abilities. Humans are extremely good at perceptual evaluation of designs, according to criteria that are extremely hard to program. As a result, they can provide fitness evaluations for evolutionary generative systems. They can also tailor the biases that generation systems use to reach useful solutions quickly. We discuss an application of these approaches: Kelly's evolutionary systems for color scheme design. Automatic design systems can work interactively with human designers by generating complete designs from partial specifications, that can then be used as starting points for designing by modification. We discuss an application of this approach: Eckert's garment shape design system.

APA, Harvard, Vancouver, ISO, and other styles

29

Singh, Montek, Utkarsh Bajpai, Vijayarajan V., and Surya Prasath. "Generation of fashionable clothes using generative adversarial networks." International Journal of Clothing Science and Technology 32, no. 2 (August 6, 2019): 177–87. http://dx.doi.org/10.1108/ijcst-12-2018-0148.

Full text

Abstract:

Purpose There are various style options available when one buys clothes on online shopping websites, however the availability the new fashion trends or choices require further user interaction in generating fashionable clothes. The paper aims to discuss this issue. Design/methodology/approach Based on generative adversarial networks (GANs) from the deep learning paradigm, here the authors suggest model system that will take the latest fashion trends and the clothes bought by users as input and generate new clothes. The new set of clothes will be based on trending fashion but at the same time will have attributes of clothes where were bought by the consumer earlier. Findings In the proposed machine learning based approach, the clothes generated by the system will personalized for different types of consumers. This will help the manufacturing companies to come up with the designs, which will directly target the customer. Research limitations/implications The biggest limitation of the collected data set is that the clothes in the two domains do not belong to a specific category. For instance the vintage clothes data set has coats, dresses, skirts, etc. These different types of clothes are not segregated. Also there is no restriction on the number of images of each type of cloth. There can many images of dresses and only a few for the coats. This can affect the end results. The aim of the paper was to find whether new and desirable clothes can be created from two different domains or not. Analyzing the impact of “the number of images for each class of cloth” is something which is aim to work in future. Practical implications The authors believe such personalized experience can increase the sales of fashion stores and here provide the feasibility of such a clothes generation system. Originality/value Applying GANs from the deep learning models for generating fashionable clothes.

APA, Harvard, Vancouver, ISO, and other styles

30

Babushkina, Anna, Marina Petrochenko, Anna Kukina, and Natalia Astafieva. "Optimizing parking lot design by Generative design approach." E3S Web of Conferences 263 (2021): 04042. http://dx.doi.org/10.1051/e3sconf/202126304042.

Full text

Abstract:

The article describes how to transform the time-consuming process of selecting design solutions for parking spaces according to regulatory requirements and terms of reference by building information modelling (BIM). The main purpose of the work is to determine the possibility of applying a generative approach to the parking lot design by creating an optimization model of variant design. The process of selecting design solutions for parking is considered by using mathematical modeling and multi-criteria optimization. A mathematical description of finding the optimal solution on the region of admissible ratios is obtained both between the two types of parking spaces required by regulatory documents (type 1-Standard, with dimensions of 5.3 × 2.5 meters; type 2 - for People with Limited Mobility (PLM), with dimensions of 6.0 × 3.6 meters) and between the occupied area and the total number of parking spaces. The optimization model of choosing design solutions for parking lot helps a design engineer to adapt changes in requirements for defining admissible options for space-planning solutions. The study proves that the task of choosing admissible and optimal solutions for the parking lot, depending on the set of conditions, can be performed by using algorithms, and, consequently, by using computer-aided design in BIM. The proposed approach to parking lot design allows the project organization to coordinate the initial conditions and solutions between the project participants and related departments, and also serves as the basis for solving subsequent design tasks, such as determining the economic efficiency, the safety of the parking project, and others.

APA, Harvard, Vancouver, ISO, and other styles

31

Flusser, Vilem. "Comments on "Generative Photography: A Systematic Constructive Approach"." Leonardo 19, no. 4 (1986): 357. http://dx.doi.org/10.2307/1578398.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Chola Raja, K., and S. Kannimuthu. "Conditional Generative Adversarial Network Approach for Autism Prediction." Computer Systems Science and Engineering 44, no. 1 (2023): 741–55. http://dx.doi.org/10.32604/csse.2023.025331.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Bosch, Anna, Andrew Zisserman, and Xavier Munoz. "Scene Classification Using a Hybrid Generative/Discriminative Approach." IEEE Transactions on Pattern Analysis and Machine Intelligence 30, no. 4 (April 2008): 712–27. http://dx.doi.org/10.1109/tpami.2007.70716.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Klõšeiko, Paul, and Peggy Freudenberg. "Generative reverse-modelling approach to hygrothermal material characterization." MATEC Web of Conferences 282 (2019): 02088. http://dx.doi.org/10.1051/matecconf/201928202088.

Full text

Abstract:

Reliable hygrothermal modelling depends on the quality of material characterization, especially so when higher moisture contents are concerned. Previous research has shown that adding additional material tests (e.g. capillary condensation redistribution (CCR) test) to the experimental dataset brings improvements to the modelling accuracy, but also adds to the workload of characterization process. This paper discusses a generative optimization workflow to increase the speed of the characterization and quality of the result. The proposed workflow incorporates optimization tool GenOpt and hygrothermal modelling software IBK Delphin to search for best fit of the water vapour and liquid conductivity curves of interior insulation materials based on modelling the CCR, drying and wet cup tests. Finally, models using material data from the proposed workflow and from the software database are compared to measurement results from two studies on interior thermal insulation. The results suggest that the generative optimization shows promise on the grounds of reducing tedious work analysing material tests. Also, a wider experimental dataset is shown to be useful when characterizing the vapour and liquid conductivity functions in over-hygroscopic region.

APA, Harvard, Vancouver, ISO, and other styles

35

Millward, Lynne J., Adrian Banks, and Kiriaki Riga. "Effective self‐regulating teams: a generative psychological approach." Team Performance Management: An International Journal 16, no. 1/2 (March 9, 2010): 50–73. http://dx.doi.org/10.1108/13527591011028924.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Bollmann, Dietrich, and Alvaro Bonfiglio. "Design Constraint Systems - A Generative Approach to Architecture." International Journal of Architectural Computing 11, no. 1 (March 2013): 37–63. http://dx.doi.org/10.1260/1478-0771.11.1.37.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Zulick, Margaret D. "Generative Rhetoric and Public Argument: A Classical Approach." Argumentation and Advocacy 33, no. 3 (January 1997): 109–19. http://dx.doi.org/10.1080/00028533.1996.11978010.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Chatzis, Sotirios P., and Gavriil Tsechpenakis. "A possibilistic clustering approach toward generative mixture models." Pattern Recognition 45, no. 5 (May 2012): 1819–25. http://dx.doi.org/10.1016/j.patcog.2011.10.010.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Vickers, Douglas. "Toward a generative transformational approach to visual perception." Behavioral and Brain Sciences 24, no. 4 (August 2001): 707–8. http://dx.doi.org/10.1017/s0140525x01680087.

Full text

Abstract:

Shepard's notion of “internalisation” is better interpreted as a simile than a metaphor. A fractal encoding model of visual perception is sketched, in which image elements are transformed in such a way as to maximise symmetry with the current input. This view, in which the transforming system embodies what has been internalised, resolves some problems raised by the metaphoric interpretation. [Hecht; Shepard]

APA, Harvard, Vancouver, ISO, and other styles

40

Ilany, Amiyaal, and Erol Akçay. "Personality and Social Networks: A Generative Model Approach." Integrative and Comparative Biology 56, no. 6 (July 1, 2016): 1197–205. http://dx.doi.org/10.1093/icb/icw068.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Chiu, P. P. K., and S. T. K. Fu. "A generative approach to Universal Cross Assembler design." ACM SIGPLAN Notices 25, no. 1 (January 3, 1990): 43–51. http://dx.doi.org/10.1145/74105.74111.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Bejar, Isaac I. "A GENERATIVE APPROACH TO PSYCHOLOGICAL AND EDUCATIONAL MEASUREMENT." ETS Research Report Series 1991, no. 1 (June 1991): i—54. http://dx.doi.org/10.1002/j.2333-8504.1991.tb01387.x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Batouta, Zouhair Ibn, Rachid Dehbi, Mohamed Talea, and Hajoui Omar. "Generative Matching Between Heterogeneous Meta-Model' Systems Based on Hybrid Heuristic." Journal of Information Technology Research 12, no. 2 (April 2019): 53–71. http://dx.doi.org/10.4018/jitr.2019040104.

Full text

Abstract:

Nowadays, designing and building computer systems has become increasingly difficult; this is essentially due to the great number of existing solutions. This article proposes a hybrid heuristic allowing the connection between meta-models of different systems, which will allow the generation between models conforming to these connected meta-models. First, this article presents the architecture of the generative matching approach named generative automatic matching (GAM), then is introduced an important part of this approach, a hybrid heuristic allowing the matching between the meta-models. Finally, the authors conclude by a multiple criteria evaluation of this approach.

APA, Harvard, Vancouver, ISO, and other styles

44

Farnoosh, Amirreza, Zhouping Wang, Shaotong Zhu, and Sarah Ostadabbas. "A Bayesian Dynamical Approach for Human Action Recognition." Sensors 21, no. 16 (August 20, 2021): 5613. http://dx.doi.org/10.3390/s21165613.

Full text

Abstract:

We introduce a generative Bayesian switching dynamical model for action recognition in 3D skeletal data. Our model encodes highly correlated skeletal data into a few sets of low-dimensional switching temporal processes and from there decodes to the motion data and their associated action labels. We parameterize these temporal processes with regard to a switching deep autoregressive prior to accommodate both multimodal and higher-order nonlinear inter-dependencies. This results in a dynamical deep generative latent model that parses meaningful intrinsic states in skeletal dynamics and enables action recognition. These sequences of states provide visual and quantitative interpretations about motion primitives that gave rise to each action class, which have not been explored previously. In contrast to previous works, which often overlook temporal dynamics, our method explicitly model temporal transitions and is generative. Our experiments on two large-scale 3D skeletal datasets substantiate the superior performance of our model in comparison with the state-of-the-art methods. Specifically, our method achieved 6.3% higher action classification accuracy (by incorporating a dynamical generative framework), and 3.5% better predictive error (by employing a nonlinear second-order dynamical transition model) when compared with the best-performing competitors.

APA, Harvard, Vancouver, ISO, and other styles

45

Li, Jie, Boyu Zhao, Kai Wu, Zhicheng Dong, Xuerui Zhang, and Zhihao Zheng. "A Representation Generation Approach of Transmission Gear Based on Conditional Generative Adversarial Network." Actuators 10, no. 5 (April 23, 2021): 86. http://dx.doi.org/10.3390/act10050086.

Full text

Abstract:

Gear reliability assessment of vehicle transmission has been a challenging issue of determining vehicle safety in the transmission industry due to a significant amount of classification errors with high-coupling gear parameters and insufficient high-density data. In terms of the preprocessing of gear reliability assessment, this paper presents a representation generation approach based on generative adversarial networks (GAN) to advance the performance of reliability evaluation as a classification problem. First, with no need for complex modeling and massive calculations, a conditional generative adversarial net (CGAN) based model is established to generate gear representations through discovering inherent mapping between features with gear parameters and gear reliability. Instead of producing intact samples like other GAN techniques, the CGAN based model is designed to learn features of gear data. In this model, to raise the diversity of produced features, a mini-batch strategy of randomly sampling from the combination of raw and generated representations is used in the discriminator, instead of using all of the data features. Second, in order to overcome the unlabeled ability of CGAN, a Wasserstein labeling (WL) scheme is proposed to tag the created representations from our model for classification. Lastly, original and produced representations are fused to train classifiers. Experiments on real-world gear data from the industry indicate that the proposed approach outperforms other techniques on operational metrics.

APA, Harvard, Vancouver, ISO, and other styles

46

Neuman, Israel. "Generative Tools for Interactive Composition: Real-Time Musical Structures Based on Schaeffer's TARTYP and on Klumpenhouwer Networks." Computer Music Journal 38, no. 2 (June 2014): 63–77. http://dx.doi.org/10.1162/comj_a_00240.

Full text

Abstract:

Interactive computer music is comparable to improvisation because it includes elements of real-time composition performed by the computer. This process of real-time composition often incorporates stochastic techniques that remap a predetermined fundamental structure to a surface of sound processing. The hierarchical structure is used to pose restrictions on the stochastic processes, but, in most cases, the hierarchical structure in itself is not created in real time. This article describes how existing musical analysis methods can be converted into generative compositional tools that allow composers to generate musical structures in real time. It proposes a compositional method based on generative grammars derived from Pierre Schaeffer's TARTYP, and describes the development of a compositional tool for real-time generation of Klumpenhouwer networks. The approach is based on the intersection of musical ideas with fundamental concepts in computer science including generative grammars, predicate logic, concepts of structural representation, and various methods of categorization.

APA, Harvard, Vancouver, ISO, and other styles

47

Pollák, M., M. Kočiško, and J. Dobránsky. "Analysis of software solutions for creating models by a generative design approach." IOP Conference Series: Materials Science and Engineering 1199, no. 1 (November 1, 2021): 012098. http://dx.doi.org/10.1088/1757-899x/1199/1/012098.

Full text

Abstract:

Abstract With the constant development of new technologies and designs, the idea of a generative design approach arose. Generative design allows to create an infinite number of new designs in a relatively short time without the constraints associated with the imagination of the designer. Designs created by a generative design approach create optimized products that meet the specific needs of their end users. The parts created in this way are often lighter, stronger and less expensive in terms of their subsequent production. Generative design software applications are often more intuitive to work with than traditional CAD systems, and no additional knowledge associated with operating the software is required. The main goal of generative design is to save time in the design process, save material by creating optimal structures, and thus save money by developing cost-effective products. The product software only adds material where it is needed, which is typical of the additive production of organic shapes and forms. The product created in this way is more efficient for production compared to the traditional design and production approach. The article points out the current state of development of this rapidly expanding design technology with a description of software solutions used for the implementation of a generative design approach on illustrative examples of created design products.

APA, Harvard, Vancouver, ISO, and other styles

48

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

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Wołczyk, Maciej, Magdalena Proszewska, Łukasz Maziarka, Maciej Zieba, Patryk Wielopolski, Rafał Kurczab, and Marek Smieja. "PluGeN: Multi-Label Conditional Generation from Pre-trained Models." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 8 (June 28, 2022): 8647–56. http://dx.doi.org/10.1609/aaai.v36i8.20843.

Full text

Abstract:

Modern generative models achieve excellent quality in a variety of tasks including image or text generation and chemical molecule modeling. However, existing methods often lack the essential ability to generate examples with requested properties, such as the age of the person in the photo or the weight of the generated molecule. Incorporating such additional conditioning factors would require rebuilding the entire architecture and optimizing the parameters from scratch. Moreover, it is difficult to disentangle selected attributes so that to perform edits of only one attribute while leaving the others unchanged. To overcome these limitations we propose PluGeN (Plugin Generative Network), a simple yet effective generative technique that can be used as a plugin to pre-trained generative models. The idea behind our approach is to transform the entangled latent representation using a flow-based module into a multi-dimensional space where the values of each attribute are modeled as an independent one-dimensional distribution. In consequence, PluGeN can generate new samples with desired attributes as well as manipulate labeled attributes of existing examples. Due to the disentangling of the latent representation, we are even able to generate samples with rare or unseen combinations of attributes in the dataset, such as a young person with gray hair, men with make-up, or women with beards. We combined PluGeN with GAN and VAE models and applied it to conditional generation and manipulation of images and chemical molecule modeling. Experiments demonstrate that PluGeN preserves the quality of backbone models while adding the ability to control the values of labeled attributes. Implementation is available at https://github.com/gmum/plugen.

APA, Harvard, Vancouver, ISO, and other styles

50

Hughes, Lloyd, Michael Schmitt, and Xiao Zhu. "Mining Hard Negative Samples for SAR-Optical Image Matching Using Generative Adversarial Networks." Remote Sensing 10, no. 10 (September 27, 2018): 1552. http://dx.doi.org/10.3390/rs10101552.

Full text

Abstract:

In this paper, we propose a generative framework to produce similar yet novel samples for a specified image. We then propose the use of these images as hard-negatives samples, within the framework of hard-negative mining, in order to improve the performance of classification networks in applications which suffer from sparse labelled training data. Our approach makes use of a variational autoencoder (VAE) which is trained in an adversarial manner in order to learn a latent distribution of the training data, as well as to be able to generate realistic, high quality image patches. We evaluate our proposed generative approach to hard-negative mining on a synthetic aperture radar (SAR) and optical image matching task. Using an existing SAR-optical matching network as the basis for our investigation, we compare the performance of the matching network trained using our approach to the baseline method, as well as to two other hard-negative mining methods. Our proposed generative architecture is able to generate realistic, very high resolution (VHR) SAR image patches which are almost indistinguishable from real imagery. Furthermore, using the patches as hard-negative samples, we are able to improve the overall accuracy, and significantly decrease the false positive rate of the SAR-optical matching task—thus validating our generative hard-negative mining approaches’ applicability to improve training in data sparse applications.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Generative approach'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles