From 6abec69eeb4660485ad86fcb94d52ece37797489 Mon Sep 17 00:00:00 2001 From: Ziming Liu Date: Sat, 17 Aug 2024 19:38:43 -0400 Subject: [PATCH] update doc tutorials --- docs/.ipynb_checkpoints/index-checkpoint.rst | 54 ++++++++++++++++---- docs/index.rst | 3 ++ 2 files changed, 46 insertions(+), 11 deletions(-) diff --git a/docs/.ipynb_checkpoints/index-checkpoint.rst b/docs/.ipynb_checkpoints/index-checkpoint.rst index 24a854e0..66cbee31 100644 --- a/docs/.ipynb_checkpoints/index-checkpoint.rst +++ b/docs/.ipynb_checkpoints/index-checkpoint.rst @@ -3,31 +3,60 @@ You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. -Welcome to Kolmogorov Aarnold Network (KAN) documentation! +Welcome to Kolmogorov Arnold Network (KAN) documentation! ========================================================== -This documentation is for the paper "KAN: Kolmogorov-Arnold Networks" and the github repo can be found here. - .. image:: kan_plot.png -Get the latest news at `CNN`_. (Add links to paper and github repo) +This documentation is for the `paper`_ "KAN: Kolmogorov-Arnold Networks" and the `github repo`_. +Kolmogorov-Arnold Networks, inspired by the Kolmogorov-Arnold representation theorem, are promising alternatives +of Multi-Layer Preceptrons (MLPs). KANs have activation functions on edges, whereas MLPs have activation functions on nodes. +This simple change makes KAN better than MLPs in terms of both accuracy and interpretability. + +.. _github repo: https://github.com/KindXiaoming/pykan +.. _paper: https://arxiv.org/abs/2404.19756 + +Installation +------------ + +Installation via github +~~~~~~~~~~~~~~~~~~~~~~~~ + +.. code-block:: python + + git clone https://github.com/KindXiaoming/pykan.git + cd pykan + pip install -e . + # pip install -r requirements.txt # install requirements -.. _CNN: http://cnn.com/ -There are two ways to install kan. The first way is via pip install +Installation via PyPI +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ .. code-block:: python - pip install kan + pip install pykan -The second way is via github + +Requirements +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ .. code-block:: python + # python==3.9.7 + matplotlib==3.6.2 + numpy==1.24.4 + scikit_learn==1.1.3 + setuptools==65.5.0 + sympy==1.11.1 + torch==2.2.2 + tqdm==4.66.2 - git clone repolink - cd kan - pip install -e . +Get started +----------- +* Quickstart: :ref:`hello-kan` +* KANs in Action: :ref:`api-demo`, :ref:`examples` +* API (advanced): :ref:`api`. .. toctree:: :maxdepth: 1 @@ -37,6 +66,9 @@ The second way is via github modules.rst demos.rst examples.rst + interp.rst + physics.rst + community.rst Indices and tables ================== diff --git a/docs/index.rst b/docs/index.rst index 6d06212e..66cbee31 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -66,6 +66,9 @@ Get started modules.rst demos.rst examples.rst + interp.rst + physics.rst + community.rst Indices and tables ==================