# An attempt to generate new bridge types from latent space of energy-based model

arXiv: https://arxiv.org/abs/2401.17657 · HTML: https://mlsanity.com/paper/2401.17657/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 8 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Builds on (most cited first, 5 of 5)

- [Learning Latent Space Energy-Based Prior Model](https://mlsanity.com/paper/2006.08205/) (2020)
- [An attempt to generate new bridge types from latent space of variational autoencoder](https://mlsanity.com/paper/2311.03380/) (2023)
- [An attempt to generate new bridge types from latent space of generative adversarial network](https://mlsanity.com/paper/2401.00700/) (2024)
- [An attempt to generate new bridge types from latent space of PixelCNN](https://mlsanity.com/paper/2401.05964/) (2024)
- [An attempt to generate new bridge types from latent space of generative flow](https://mlsanity.com/paper/2401.10299/) (2024)

## Built on by (most cited first, 1 of 1)

- [Aided design of bridge aesthetics based on Stable Diffusion fine-tuning](https://mlsanity.com/paper/2409.15812/) (2024)

## Abstract (arXiv)

Use energy-based model for bridge-type innovation. The loss function is explained by the game theory, the logic is clear and the formula is simple and clear. Thus avoid the use of maximum likelihood estimation to explain the loss function and eliminate the need for Monte Carlo methods to solve the normalized denominator. Assuming that the bridge-type population follows a Boltzmann distribution, a neural network is constructed to represent the energy function. Use Langevin dynamics technology to generate a new sample with low energy value, thus a generative model of bridge-type based on energy is established. Train energy function on symmetric structured image dataset of three span beam bridge, arch bridge, cable-stayed bridge, and suspension bridge to accurately calculate the energy values of real and fake samples. Sampling from latent space, using gradient descent algorithm, the energy function transforms the sampling points into low energy score samples, thereby generating new bridge types different from the dataset. Due to unstable and slow training in this attempt, the possibility of generating new bridge types is rare and the image definition of generated images is low.