SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.12722 · AAAI · 2023

Learning Fractals by Gradient Descent

Wei-Lun Chao, Hong-You Chen, Cheng-Hao Tu, David Carlyn

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
andytu28/LearningFractals — 3 of 4
FunctionStatusWhere it lives
forward_pass_iterate_svdformat Ran andytu28/LearningFractals/deep_fractal.py
code served (permissive licence) · get_code("d516f571fdb9d435")
make_diagnal_matrix Ran andytu28/LearningFractals/deep_fractal.py
code served (permissive licence) · get_code("b604b8cad31eeac0")
make_matrices_from_svdformat Ran andytu28/LearningFractals/deep_fractal.py
code served (permissive licence) · get_code("1067f8586cbb176d")
make_rotation_matrix Not yet run andytu28/LearningFractals/deep_fractal.py
code served (permissive licence) · get_code("a38980a23a258ca0")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Fractals are geometric shapes that can display complex and self-similar patterns found in nature (e.g., clouds and plants). Recent works in visual recognition have leveraged this property to create random fractal images for model pre-training. In this paper, we study the inverse problem -given a target image (not necessarily a fractal), we aim to generate a fractal image that looks like it. We propose a novel approach that learns the parameters underlying a fractal image via gradient descent. We show that our approach can find fractal parameters of high visual quality and be compatible with different loss functions, opening up several potentials, e.g., learning fractals for downstream tasks, scientific understanding, etc.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.12722")
get_code_for_paper("2303.12722")
have("2303.12722")

Connect an agent — have() is free.