Representation Learning for Sequential Volumetric Design Tasks
- URL: http://arxiv.org/abs/2309.02583v1
- Date: Tue, 5 Sep 2023 21:21:06 GMT
- Title: Representation Learning for Sequential Volumetric Design Tasks
- Authors: Md Ferdous Alam, Yi Wang, Linh Tran, Chin-Yi Cheng, Jieliang Luo
- Abstract summary: We propose to encode the design knowledge from a collection of expert or high-performing design sequences and extract useful representations using transformer-based models.
We develop the preference model by estimating the density of the learned representations whereas we train an autoregressive transformer model for sequential design generation.
Our preference model can compare two arbitrarily given design sequences and is almost 90% accurate in evaluation against random design sequences.
- Score: 16.601382689846943
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Volumetric design, also called massing design, is the first and critical step
in professional building design which is sequential in nature. As the
volumetric design process is complex, the underlying sequential design process
encodes valuable information for designers. Many efforts have been made to
automatically generate reasonable volumetric designs, but the quality of the
generated design solutions varies, and evaluating a design solution requires
either a prohibitively comprehensive set of metrics or expensive human
expertise. While previous approaches focused on learning only the final design
instead of sequential design tasks, we propose to encode the design knowledge
from a collection of expert or high-performing design sequences and extract
useful representations using transformer-based models. Later we propose to
utilize the learned representations for crucial downstream applications such as
design preference evaluation and procedural design generation. We develop the
preference model by estimating the density of the learned representations
whereas we train an autoregressive transformer model for sequential design
generation. We demonstrate our ideas by leveraging a novel dataset of thousands
of sequential volumetric designs. Our preference model can compare two
arbitrarily given design sequences and is almost 90% accurate in evaluation
against random design sequences. Our autoregressive model is also capable of
autocompleting a volumetric design sequence from a partial design sequence.
Related papers
- I-Design: Personalized LLM Interior Designer [57.00412237555167]
I-Design is a personalized interior designer that allows users to generate and visualize their design goals through natural language communication.
I-Design starts with a team of large language model agents that engage in dialogues and logical reasoning with one another.
The final design is then constructed in 3D by retrieving and integrating assets from an existing object database.
arXiv Detail & Related papers (2024-04-03T16:17:53Z) - Compositional Generative Inverse Design [69.22782875567547]
Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem.
We show that by instead optimizing over the learned energy function captured by the diffusion model, we can avoid such adversarial examples.
In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes.
arXiv Detail & Related papers (2024-01-24T01:33:39Z) - Machine Learning-Based Multi-Objective Design Exploration Of Flexible
Disc Elements [1.5638419778920147]
This paper showcases Artificial Neural Network (ANN) architecture applied to an engineering design problem to explore and identify improved design solutions.
The case problem of this study is the design of flexible disc elements used in disc couplings.
To accomplish this objective, we employ ANN coupled with genetic algorithm in the design exploration step to identify designs that meet the specified criteria.
arXiv Detail & Related papers (2023-04-14T16:48:51Z) - Efficient Quality Diversity Optimization of 3D Buildings through 2D
Pre-optimization [101.18253437732933]
Quality diversity algorithms can be used to create a diverse set of solutions to inform engineers' intuition.
But quality diversity is not efficient in very expensive problems, needing 100.000s of evaluations.
We show that we can produce better machine learning models by producing training data with quality diversity.
arXiv Detail & Related papers (2023-03-28T11:20:59Z) - Design Space Exploration and Explanation via Conditional Variational
Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges [52.77024349608834]
This paper provides a performance-driven design exploration framework to augment the human designer through a Conditional Variational Autoencoder (CVAE)
The CVAE is trained on 18'000 synthetically generated instances of a pedestrian bridge in Switzerland.
arXiv Detail & Related papers (2022-11-29T17:28:31Z) - Efficient Automatic Machine Learning via Design Graphs [72.85976749396745]
We propose FALCON, an efficient sample-based method to search for the optimal model design.
FALCON features 1) a task-agnostic module, which performs message passing on the design graph via a Graph Neural Network (GNN), and 2) a task-specific module, which conducts label propagation of the known model performance information.
We empirically show that FALCON can efficiently obtain the well-performing designs for each task using only 30 explored nodes.
arXiv Detail & Related papers (2022-10-21T21:25:59Z) - Investigating Positive and Negative Qualities of Human-in-the-Loop
Optimization for Designing Interaction Techniques [55.492211642128446]
Designers reportedly struggle with design optimization tasks where they are asked to find a combination of design parameters that maximizes a given set of objectives.
Model-based computational design algorithms assist designers by generating design examples during design.
Black box methods for assistance, on the other hand, can work with any design problem.
arXiv Detail & Related papers (2022-04-15T20:40:43Z) - iPLAN: Interactive and Procedural Layout Planning [13.172253981084403]
We propose a new human-in-the-loop generative model, iPLAN.
It is capable of automatically generating layouts, but also interacting with designers throughout the whole procedure.
The results show that iPLAN has high fidelity in producing similar layouts to those from human designers.
arXiv Detail & Related papers (2022-03-27T23:21:15Z) - Physical Design using Differentiable Learned Simulators [9.380022457753938]
In inverse design, learned forward simulators are combined with gradient-based design optimization.
This framework produces high-quality designs by propagating through trajectories of hundreds of steps.
Our results suggest that despite some remaining challenges, machine learning-based simulators are maturing to the point where they can support general-purpose design optimization.
arXiv Detail & Related papers (2022-02-01T19:56:39Z) - Generative Design by Reinforcement Learning: Enhancing the Diversity of
Topology Optimization Designs [5.8010446129208155]
This study proposes a reinforcement learning based generative design process, with reward functions maximizing the diversity of topology designs.
We show that RL-based generative design produces a large number of diverse designs within a short inference time by exploiting GPU in a fully automated manner.
arXiv Detail & Related papers (2020-08-17T06:50:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.