A Machine Learning Application Based On Giorgio Morandi Still Life Paintings To Assist Artists In The Choice Of 3d Compositions

Leonardo ◽  
2021 ◽  
pp. 1-8
Author(s):  
Guido Salimbeni ◽  
Frederic Fol Leymarie ◽  
William Latham
Keyword(s):  
Machine Learning ◽  
Creative Process ◽  
Three Dimensional ◽  
Still Life ◽  
Generative Adversarial Network ◽  
Aesthetic Evaluation ◽  
Adversarial Network ◽  
The Media ◽  
Dimensional Models ◽  
Three Dimensional Models

Abstract We present a system built to generate arrangements of three-dimensional models for aesthetic evaluation, with the aim to support an artist in their creative process. We explore how this system can automatically generate aesthetically pleasing content for use in the media and design industry, based on standards originally developed in master artworks. We demonstrate the effectiveness of our process in the context of paintings using a collection of images inspired by the work of the artist Giorgio Morandi (Bologna, 1890 -- 1964). Finally, we compare the results of our system with the results of a well-known Generative Adversarial Network (GAN).

scholarly journals Synthesis and Computer Study of Population Dynamics Controlled Models Using Methods of Numerical Optimization, Stochastization and Machine Learning

Mathematics ◽  
2021 ◽  
Vol 9 (24) ◽  
pp. 3303
Author(s):  
Anastasia V. Demidova ◽  
Olga V. Druzhinina ◽  
Olga N. Masina ◽  
Alexey A. Petrov
Keyword(s):  
Machine Learning ◽  
Population Dynamics ◽  
Numerical Optimization ◽  
Numerical Study ◽  
Three Dimensional ◽  
Equilibrium States ◽  
Optimal Trajectories ◽  
Trophic Chains ◽  
Dimensional Models ◽  
Three Dimensional Models

The problems of synthesis and analysis of multidimensional controlled models of population dynamics are of both theoretical and applied interest. The need to solve numerical optimization problems for such a class of models is associated with the expansion of ecosystem control requirements. The need to solve the problem of stochastization is associated with the emergence of new problems in the study of ecological systems properties under the influence of random factors. The aim of the work is to develop a new approach to studying the properties of population dynamics systems using methods of numerical optimization, stochastization and machine learning. The synthesis problems of nonlinear three-dimensional models of interconnected species number dynamics, taking into account trophic chains and competition in prey populations, are studied. Theorems on the asymptotic stability of equilibrium states are proved. A qualitative and numerical study of the models is carried out. Using computational experiments, the results of an analytical stability and permanent coexistence study are verified. The search for equilibrium states belonging to the stability and permanent coexistence region is made using the developed intelligent algorithm and evolutionary calculations. The transition is made from the model specified by the vector ordinary differential equation to the corresponding stochastic model. A comparative analysis of deterministic and stochastic models with competition and trophic chains is carried out. New effects are revealed that are characteristic of three-dimensional models, taking into account the competition in populations of prey. The formulation of the optimal control problem for a model with competition and trophic chains is proposed. To find optimal trajectories, new generalized algorithms for numerical optimization are developed. A methods for the synthesis of controllers based on the use of artificial neural networks and machine learning are developed. The results on the search for optimal trajectories and generation of control functions are presented.The obtained results can be used in modeling problems of ecological, demographic, socio-economic and chemical kinetics systems.

scholarly journals Print-and-Play Fabrication

2021 ◽  
Author(s):  
Carlos E. Tejada
Keyword(s):  
Machine Learning ◽  
Three Dimensional ◽  
Digital Fabrication ◽  
Learning Models ◽  
Fluid Behavior ◽  
The Status ◽  
Physical Shape ◽  
Dimensional Models ◽  
Three Dimensional Models ◽  
Machine Learning Models

In recent years, it has become increasingly accessible to create interactive applications on screen-based devices. Contrary to this ease, and despite their numerous benefits, creating tangible interactive devices is a task reserved for experts, requiring extensive knowledge on electronics, and manual assemblies. While digital fabrication equipment holds promise to alleviate this situation, the majority of research exploring this avenue still present significant barriers for non-experts, and other-domain experts to construct tangible devices, often requiring assembly of electronic circuits and printed parts, prohibitive fabrication pipelines, or intricate calibration of machine learning models. This thesis introduces Print-and-Play Fabrication: a digital fabrication paradigm where tangible interactive devices are printed, rather than assembled. By embedding interior structures inside three-dimensional models that leverage distinct properties of fluid behavior, this thesis presents a variety of techniques to construct tangible devices that can sense, process, and respond to user’s interactions without requiring assembly of parts, circuits, or calibration of machine learning models. Chapter 2 provides an overview of the fabrication of tangible devices literature through the lens of Print-and-Play Fabrication. This chapter highlights the post-print activities required to enable each of the efforts in the literature, and reflects on the status of the field. Chapters 3 and 4 introduce two novel techniques for constructing tangible devices that can sense user’s interactions. AirTouch uses basic principles of fluid behavior to enable the construction of touch-sensing devices, capable of detecting interactions in up to 12 locations, with an accuracy of up to 98%. Blowhole builds on this concept by employing principles of acoustic resonance to construct tangible devices that can detect where they are gently blown on. Blowhole-enabled devices can enable up to seven interactive locations, with an accuracy of up to 98%. Conversely, in Chapter 6 I introduce a technique to encapsulate logic computation into 3D-printed objects. Inspired by concepts from the Cold War era, I embed structures capable of representing basic logic operations using interacting jets of air into three-dimensional models. AirLogic takes the form of a toolkit, enabling non-expert designers to add a variety of input, logic processing, and output mechanisms to three-dimensional models. Continuing, Chapter 5 describes a toolkit for fabricating objects capable of changing their physical shape using pneumatic actuation. MorpheesPlug introduces a design environment, a set of pneumatically actuated widgets, and a control module that, in tandem, enable non[1]experts to construct devices capable of changing their physical shape in order to provide output. Last, I conclude with reflections on the status of Print-and-Play Fabrication, and possible directions for future work.

scholarly journals 3D Model Generation on Architectural Plan and Section Training through Machine Learning

Technologies ◽  
2019 ◽  
Vol 7 (4) ◽  
pp. 82
Author(s):  
Hang Zhang
Keyword(s):  
Machine Learning ◽  
3D Model ◽  
Three Dimensional ◽  
Image Data ◽  
Input Image ◽  
Model Generation ◽  
Three Dimensional Model ◽  
Generative Adversarial Network ◽  
Learning Group ◽  
Adversarial Network

Machine learning, especially the GAN (Generative Adversarial Network) model, has been developed tremendously in recent years. Since the NVIDIA Machine Learning group presented the StyleGAN in December 2018, it has become a new way for designers to make machines learn different or similar types of architectural photos, drawings, and renderings, then generate (a) similar fake images, (b) style-mixing images, and (c) truncation trick images. The author both collected and created input image data, and specially made architectural plan and section drawing inputs with a clear design purpose, then applied StyleGAN to train specific networks on these datasets. With the training process, we could look into the deep relationship between these input architectural plans or sections, then generate serialized transformation images (truncation trick images) to form the 3D (three-dimensional) model with a decent resolution (up to 1024 × 1024 × 1024 pixels). Though the results of the 3D model generation are difficult to use directly in 3D spatial modeling, these unexpected 3D forms still could inspire new design methods and greater possibilities of architectural plan and section design.

Plastic replicas as three-dimensional models of pulps

1975 ◽  
Vol 39 (8) ◽  
pp. 544-546
Author(s):  
HL Wakkerman ◽  
GS The ◽  
AJ Spanauf
Keyword(s):  
Three Dimensional ◽  
Dimensional Models ◽  
Three Dimensional Models

ORGANIC (1).pdf

2017 ◽  
Author(s):  
Benjamin Sanchez-Lengeling ◽  
Carlos Outeiral ◽  
Gabriel L. Guimaraes ◽  
Alan Aspuru-Guzik
Keyword(s):  
Machine Learning ◽  
Learning Community ◽  
Chemical Species ◽  
Material Design ◽  
Organic Photovoltaic ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Photovoltaic Material

Molecular discovery seeks to generate chemical species tailored to very specific needs. In this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative Adversarial Networks (ORGAN), capable of producing a distribution over molecular space that matches with a certain set of desirable metrics. This methodology combines two successful techniques from the machine learning community: a Generative Adversarial Network (GAN), to create non-repetitive sensible molecular species, and Reinforcement Learning (RL), to bias this generative distribution towards certain attributes. We explore several applications, from optimization of random physicochemical properties to candidates for drug discovery and organic photovoltaic material design.

In Silico Identification and Molecular Characterization of Extracellular Cathepsin L Proteases from Giardia duodenalis

2020 ◽  
Vol 17 (4) ◽  
pp. 342-351
Author(s):  
Sergio A. Durán-Pérez ◽  
José G. Rendón-Maldonado ◽  
Lucio de Jesús Hernandez-Diaz ◽  
Annete I. Apodaca-Medina ◽  
Maribel Jiménez-Edeza ◽  
...  
Keyword(s):  
In Silico ◽  
Cathepsin L ◽  
Three Dimensional ◽  
Giardia Duodenalis ◽  
Evolutionary Genetics ◽  
Extracellular Proteins ◽  
In Silico Identification ◽  
Dimensional Models ◽  
Three Dimensional Models

Background: The protozoan Giardia duodenalis, which causes giardiasis, is an intestinal parasite that commonly affects humans, mainly pre-school children. Although there are asymptomatic cases, the main clinical features are chronic and acute diarrhea, nausea, abdominal pain, and malabsorption syndrome. Little is currently known about the virulence of the parasite, but some cases of chronic gastrointestinal alterations post-infection have been reported even when the infection was asymptomatic, suggesting that the cathepsin L proteases of the parasite may be involved in the damage at the level of the gastrointestinal mucosa. Objective: The aim of this study was the in silico identification and characterization of extracellular cathepsin L proteases in the proteome of G. duodenalis. Methods: The NP_001903 sequence of cathepsin L protease from Homo sapienswas searched against the Giardia duodenalisproteome. The subcellular localization of Giardia duodenaliscathepsin L proteases was performed in the DeepLoc-1.0 server. The construction of a phylogenetic tree of the extracellular proteins was carried out using the Molecular Evolutionary Genetics Analysis software (MEGA X). The Robetta server was used for the construction of the three-dimensional models. The search for possible inhibitors of the extracellular cathepsin L proteases of Giardia duodenaliswas performed by entering the three-dimensional structures in the FINDSITEcomb drug discovery tool. Results: Based on the amino acid sequence of cathepsin L from Homo sapiens, 8 protein sequences were identified that have in their modular structure the Pept_C1A domain characteristic of cathepsins and two of these proteins (XP_001704423 and XP_001704424) are located extracellularly. Threedimensional models were designed for both extracellular proteins and several inhibitory ligands with a score greater than 0.9 were identified. In vitrostudies are required to corroborate if these two extracellular proteins play a role in the virulence of Giardia duodenalisand to discover ligands that may be useful as therapeutic targets that interfere in the mechanism of pathogenesis generated by the parasite. Conclusion: In silicoanalysis identified two proteins in the Giardia duodenalisprotein repertoire whose characteristics allowed them to be classified as cathepsin L proteases, which may be secreted into the extracellular medium to act as virulence factors. Three-dimensional models of both proteins allowed the identification of inhibitory ligands with a high score. The results suggest that administration of those compounds might be used to block the endopeptidase activity of the extracellular cathepsin L proteases, interfering with the mechanisms of pathogenesis of the protozoan parasite Giardia duodenalis.

Sign in / Sign up

Export Citation Format

Share Document