Mapping generative models for architectural design

2021 ◽  
pp. 29-58
Author(s):  
Pedro Veloso ◽  
Ramesh Krishnamurti
Keyword(s):  
Architectural Design ◽  
Generative Models

scholarly journals A Survey on Variational Autoencoders from a Green AI Perspective

2021 ◽  
Vol 2 (4) ◽  
Author(s):  
Andrea Asperti ◽  
Davide Evangelista ◽  
Elena Loli Piccolomini
Keyword(s):  
Architectural Design ◽  
Mathematical Formulation ◽  
Representation Learning ◽  
Generative Models ◽  
Model Description ◽  
Energetic Efficiency ◽  
Detailed Model ◽  
Latent Distribution ◽  
Quantitative Results ◽  
Generation Problem

AbstractVariational Autoencoders (VAEs) are powerful generative models that merge elements from statistics and information theory with the flexibility offered by deep neural networks to efficiently solve the generation problem for high-dimensional data. The key insight of VAEs is to learn the latent distribution of data in such a way that new meaningful samples can be generated from it. This approach led to tremendous research and variations in the architectural design of VAEs, nourishing the recent field of research known as unsupervised representation learning. In this article, we provide a comparative evaluation of some of the most successful, recent variations of VAEs. We particularly focus the analysis on the energetic efficiency of the different models, in the spirit of the so-called Green AI, aiming both to reduce the carbon footprint and the financial cost of generative techniques. For each architecture, we provide its mathematical formulation, the ideas underlying its design, a detailed model description, a running implementation and quantitative results.

Nanotectonica: Architectural Design Studio and Table Top SEM

2008 ◽  
Vol 16 (5) ◽  
pp. 40-43
Author(s):  
Jonas Coersmeier ◽  
Donovan N. Leonard
Keyword(s):  
Architectural Design ◽  
Generative Models ◽  
Design Studio ◽  
Research Seminar ◽  
Large Span ◽  
Mother Nature ◽  
Macro Scale ◽  
Buckminster Fuller ◽  
Design Students ◽  
Architectural Design Studio

Inspired by architect Frei Otto and design scientist Buckminster Fuller, third year Pratt Institute design students from Jonas Coersmeier’s design studio and research seminar (of Spring 2008) utilized a Table Top SEM to observe micro and nano-scale features produced solely by Mother Nature. After analyzing and documenting the intricacy, beauty and functionality of natural structures, students selected structural entities typically not observed on the macro scale, and utilized the micrograph data to generate analytical drawings followed by generative models for design of a large span structure that would become an aquatic center in the Williamsburg neighborhood of Brooklyn, N.Y.

Elements of Architectural Design

1888 ◽  
Vol 25 (647supp) ◽  
pp. 10339-10341
Author(s):  
H. H. Statham
Keyword(s):  
Architectural Design

Proposal for Refugee Housing in Southeast Europe Utilizing Regionally Appropriate, Sustainable, and Affordable Construction Methods

2020 ◽  
Vol 22 ◽  
Author(s):  
Hana Cicevic ◽  
Sarah Gamble
Keyword(s):  
Architectural Design ◽  
Housing Demand ◽  
Situational Factors ◽  
Housing Unit ◽  
Southeast Europe ◽  
Construction Methods ◽  
Permanent Housing ◽  
Emergency Housing ◽  
Communal Housing ◽  
Construction Model

This research focuses on the emergency-housing demand caused by the on-going refugee crisis in Southeastern Europe. The research and proposed solutions focus on Northern Serbia, as this region generally lacks permanent housing solutions for accommodating the increasing influx of immigrants. The outcome of this research is an architectural proposal for the refugee housing unit designed particularly for the situational factors of this focus region.    The study identifies earth architecture as the primary building technique, due to its ability to satisfy a range of defined end-product goals.  These goals include: the sustainability of the material, quality and durability of the final product, skill level required for non-professional construction, final cost of material and execution, historical regional precedent, and opportunity for communal engagement of the immigrant population. The proposed architectural design uses earth-bag construction as the sub-method most suitable for this location and in keeping with the goals outlined above. The proposed housing unit is a singular component that could be duplicated to create larger communal housing communities.  A broad overview of possible solutions is included, followed by the development of the earth-bag construction option. The development of this proposal includes material studies, sketches, and an architectural model as representation tools. The outcomes of this research serve as a guideline, rather than a precise construction model, in creating much needed refugee housing communities in North Serbia.      

On Methodology for Designing Architectural Lighting of Production Site Interior

2020 ◽  
pp. 10-21 ◽  
Author(s):  
Vladimir V. Voronov ◽  
Nikolay I. Shchepetkov
Keyword(s):  
Architectural Design ◽  
Comprehensive Approach ◽  
Scientific Methodology ◽  
Field Observations ◽  
Production Site ◽  
Artificial Illumination ◽  
Engineering Parameters ◽  
Architectural Lighting ◽  
Candidate Thesis

The article describes content of original and relevant but virtually forgotten thesis of V.V. Voronov on lighting of production site interiors by means of overhead natural (using three types of skylights) and artificial illumination, in order to elaborate scientific methodology for architectural design of more qualitative luminous environment on the basis of comprehensive approach and enhanced criteria framework of its evaluation using light engineering parameters. The thesis is unique in terms of the scope and quality of field and laboratory observations which are reflected not only in the text but also in the graphical attachments, namely photos, figures, schemes, drawings, charts, nomograms, and diagrams accompanied by specific measured or calculated parameters. The first part of the thesis contains theoretical basics and results of field observations conducted by different methods. This second part is the exposition of chapter 3 of the V.V. Voronov’s candidate thesis (1985). It describes the methodology for and the results of the experiments by means of planar and volumetric light simulation using the architectural lighting simulating assembly (chamber) which were conducted in MARKHI in 1970–1985.

ARCHITECTURAL DESIGN KEYWORDS OF INCEPTION SPACE

2019 ◽  
Vol 6 (2) ◽  
pp. 61
Author(s):  
Muhammad Heru Arie Edytia ◽  
Zulhadi Sahputra ◽  
Mirza Mirza
Keyword(s):  
Architectural Design ◽  
Positive Emotions ◽  
Main Design ◽  
Architectural Space ◽  
Space Design ◽  
People With Dementia ◽  
Space Potential ◽  
Design Mechanism ◽  
Christopher Nolan ◽  
And Behavior

This paper explains the idea of inception space from Inception (2010), a movie directed by Christopher Nolan, to explore the inception space potential in designing architectural space. Inception space is an architectural space design mechanism that translates the essential experience of space users as an effort to implant idea in the form of positive emotions. In other words, the architectural space is a medium of inception to a space user or a target (mark). The main purpose of inception space design is to affect the target (mark) by planting the idea ‘secretly’. The target is unaware of the intervention and considers the idea presented itself. This process becomes the beginning of an idea to grow in one's mind the beginning of mindset and behavior change. In other words, architects or planners can apply this mechanism to design and influence users so that the design success rate can be improved. The main design keywords as part of the inception process are perception, memory, scenario, layer, and labyrinth. The development of design methods of inception space can be explored and applied to different targets and contexts by applying these design keywords. For example, this design mechanism can be applied to people with dementia who experience memory and visuospatial deficit through wayfinding programming.

Molecular Generation Targeting Desired Electronic Properties via Deep Generative Models

2019 ◽  
Author(s):  
Qi Yuan ◽  
Alejandro Santana-Bonilla ◽  
Martijn Zwijnenburg ◽  
Kim Jelfs
Keyword(s):  
Neural Network ◽  
Electronic Properties ◽  
Transfer Learning ◽  
Recurrent Neural Network ◽  
Chemical Space ◽  
Generative Models ◽  
Molecular Features ◽  
Donor Acceptor ◽  
Homo Lumo ◽  
Training Sets

<p>The chemical space for novel electronic donor-acceptor oligomers with targeted properties was explored using deep generative models and transfer learning. A General Recurrent Neural Network model was trained from the ChEMBL database to generate chemically valid SMILES strings. The parameters of the General Recurrent Neural Network were fine-tuned via transfer learning using the electronic donor-acceptor database from the Computational Material Repository to generate novel donor-acceptor oligomers. Six different transfer learning models were developed with different subsets of the donor-acceptor database as training sets. We concluded that electronic properties such as HOMO-LUMO gaps and dipole moments of the training sets can be learned using the SMILES representation with deep generative models, and that the chemical space of the training sets can be efficiently explored. This approach identified approximately 1700 new molecules that have promising electronic properties (HOMO-LUMO gap <2 eV and dipole moment <2 Debye), 6-times more than in the original database. Amongst the molecular transformations, the deep generative model has learned how to produce novel molecules by trading off between selected atomic substitutions (such as halogenation or methylation) and molecular features such as the spatial extension of the oligomer. The method can be extended as a plausible source of new chemical combinations to effectively explore the chemical space for targeted properties.</p>

Sign in / Sign up

Export Citation Format

Share Document