Papers

Improving Convolutional Neural Networks for Cosmological Fields with Random Permutation

K Zhong, M Gatti, B Jain - arXiv preprint arXiv:2403.01368, 2024 - arxiv.org

… We use simulation-based inference (SBI) to show that the model outperforms CNN designs in the literature. We find a 30% improvement in the constraints of the 𝑆8 …

Link to paper

BibTeX

@misc{zhong2024improving,
      title={Improving Convolutional Neural Networks for Cosmological Fields with Random Permutation}, 
      author={Kunhao Zhong and Marco Gatti and Bhuvnesh Jain},
      year={2024},
      eprint={2403.01368},
      archivePrefix={arXiv},
      primaryClass={astro-ph.CO}
}

Share