Neural topology optimization: the good, the bad, and the ugly

• URL: http://arxiv.org/abs/2407.13954v1
• Date: Fri, 19 Jul 2024 00:10:56 GMT
• Title: Neural topology optimization: the good, the bad, and the ugly
• Authors: Suryanarayanan Manoj Sanu, Alejandro M. Aragon, Miguel A. Bessa,
• Abstract summary: Neural networks (NNs) hold great promise for advancing inverse via topology optimization (TO) Yet misconceptions about their application persist. This article focuses on topology optimization (neural landscape) While still in infancy, our analysis tools reveal critical insights into the NN architecture.
• Score: 44.99833362998488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural networks (NNs) hold great promise for advancing inverse design via topology optimization (TO), yet misconceptions about their application persist. This article focuses on neural topology optimization (neural TO), which leverages NNs to reparameterize the decision space and reshape the optimization landscape. While the method is still in its infancy, our analysis tools reveal critical insights into the NNs' impact on the optimization process. We demonstrate that the choice of NN architecture significantly influences the objective landscape and the optimizer's path to an optimum. Notably, NNs introduce non-convexities even in otherwise convex landscapes, potentially delaying convergence in convex problems but enhancing exploration for non-convex problems. This analysis lays the groundwork for future advancements by highlighting: 1) the potential of neural TO for non-convex problems and dedicated GPU hardware (the "good"), 2) the limitations in smooth landscapes (the "bad"), and 3) the complex challenge of selecting optimal NN architectures and hyperparameters for superior performance (the "ugly").

Related papers

• Neural Networks for Generating Better Local Optima in Topology Optimization [0.4543820534430522]
  We show how neural network material discretizations can, under certain conditions, find better local optima in more challenging optimization problems. We emphasize that the neural network material discretization's advantage comes from the interplay with its current limitations.
  arXiv  Detail & Related papers  (2024-07-25T11:24:44Z)
• Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy [75.15685966213832]
  We analyze the rich directional structure of optimization trajectories represented by their pointwise parameters. We show that training only scalar batchnorm parameters some while into training matches the performance of training the entire network.
  arXiv  Detail & Related papers  (2024-03-12T07:32:47Z)
• Neural Optimization Machine: A Neural Network Approach for Optimization [10.283797653337132]
  A novel neural network (NN) approach is proposed for constrained optimization. The proposed method uses a specially designed NN architecture and training/optimization procedure called Neural Optimization Machine (NOM)
  arXiv  Detail & Related papers  (2022-08-08T03:34:58Z)
• Neural Improvement Heuristics for Graph Combinatorial Optimization Problems [49.85111302670361]
  We introduce a novel Neural Improvement (NI) model capable of handling graph-based problems where information is encoded in the nodes, edges, or both. The presented model serves as a fundamental component for hill-climbing-based algorithms that guide the selection of neighborhood operations for each.
  arXiv  Detail & Related papers  (2022-06-01T10:35:29Z)
• NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo [97.07453889070574]
  We present a new multi-view depth estimation method that utilizes both conventional SfM reconstruction and learning-based priors. We show that our proposed framework significantly outperforms state-of-the-art methods on indoor scenes.
  arXiv  Detail & Related papers  (2021-09-02T17:54:31Z)
• What can linear interpolation of neural network loss landscapes tell us? [11.753360538833139]
  Loss landscapes are notoriously difficult to visualize in a human-comprehensible fashion. One common way to address this problem is to plot linear slices of the landscape.
  arXiv  Detail & Related papers  (2021-06-30T11:54:04Z)
• A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks [23.038631072178735]
  We consider a broad class of optimization algorithms that are commonly used in practice. As a consequence, we can leverage the convergence behavior of neural networks. We believe our approach can also be extended to other optimization algorithms and network theory.
  arXiv  Detail & Related papers  (2020-10-25T17:10:22Z)
• Persistent Neurons [4.061135251278187]
  We propose a trajectory-based strategy that optimize the learning task using information from previous solutions. Persistent neurons can be regarded as a method with gradient informed bias where individual updates are corrupted by deterministic error terms. We evaluate the full and partial persistent model and show it can be used to boost the performance on a range of NN structures.
  arXiv  Detail & Related papers  (2020-07-02T22:36:49Z)
• The Hidden Convex Optimization Landscape of Two-Layer ReLU Neural Networks: an Exact Characterization of the Optimal Solutions [51.60996023961886]
  We prove that finding all globally optimal two-layer ReLU neural networks can be performed by solving a convex optimization program with cone constraints. Our analysis is novel, characterizes all optimal solutions, and does not leverage duality-based analysis which was recently used to lift neural network training into convex spaces.
  arXiv  Detail & Related papers  (2020-06-10T15:38:30Z)
• Self-Directed Online Machine Learning for Topology Optimization [58.920693413667216]
  Self-directed Online Learning Optimization integrates Deep Neural Network (DNN) with Finite Element Method (FEM) calculations. Our algorithm was tested by four types of problems including compliance minimization, fluid-structure optimization, heat transfer enhancement and truss optimization. It reduced the computational time by 2 5 orders of magnitude compared with directly using methods, and outperformed all state-of-the-art algorithms tested in our experiments.
  arXiv  Detail & Related papers  (2020-02-04T20:00:28Z)

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.