Merge pull request mintisan#125 from silvermete0r/main

mintisan · web-flow · commit 66581533ce50 · 2025-06-30T21:28:55.000+08:00
Updated `OIKAN` description to "KART-inspired Neuro-Symbolic ML"
diff --git a/README.md b/README.md
@@ -142,10 +142,11 @@ A curated list of awesome libraries, projects, tutorials, papers, and other reso
 - [SigKAN](https://github.com/remigenet/SigKAN): Path Signature-Weighted Kolmogorov-Arnold Networks tensorflow 2.x layer implementations, based on iisignature | ![Github stars](https://img.shields.io/github/stars/remigenet/sigkan.svg)
 - [KAN-SGAN](https://github.com/hoangthangta/KAN-SGAN/): Semi-supervised learning with Generative Adversarial Networks (GANs) using Kolmogorov-Arnold Network Layers (KANLs) | ![Github stars](https://img.shields.io/github/stars/hoangthangta/KAN-SGAN.svg)
 - [HiPPO-KAN: Efficient KAN Model for Time Series Analysis](https://arxiv.org/abs/2410.14939)
-- [OIKAN](https://github.com/silvermete0r/oikan): Optimized Interpretable Kolmogorov-Arnold Networks | ![Github stars](https://img.shields.io/github/stars/silvermete0r/oikan.svg)
+- [OIKAN](https://github.com/silvermete0r/oikan): Neuro-Symbolic ML for Scientific Discovery (not a direct implementation of KANs but a KART-inspired alternative to make more efficient and accurate Neuro-Symbolic ML) | ![Github stars](https://img.shields.io/github/stars/silvermete0r/oikan.svg)
 - [timeKAN](https://github.com/SamerMakni/timekan):  Kolmogorov-Arnold Networks with recurrent architectures | ![Github stars](https://img.shields.io/github/stars/SamerMakni/timekan)
 - [MatrixKAN](https://github.com/OSU-STARLAB/MatrixKAN): MatrixKAN: An optimized B-spline-based KAN implementation with superior effective computation time for higher spline degrees and larger datasets | ![Github stars](https://img.shields.io/github/stars/OSU-STARLAB/MatrixKAN.svg)
 
+
 ### Library-based
 
 - [TorchKAN](https://github.com/1ssb/torchkan) : Simplified KAN Model Using Legendre approximations and Monomial basis functions for Image Classification for MNIST. Achieves 99.5% on MNIST using Conv+LegendreKAN.   ｜ ![Github stars](https://img.shields.io/github/stars/1ssb/torchkan.svg)
