Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A Python package that uses task-based neurons to build neural networks.
| Date | Stars |
|---|---|
| 2026-07-31 | 283 |
| 2026-08-01 | 283 |
| 2026-08-02 | 283 |
| 2026-08-05 | 284 |
| 2026-08-06 | 284 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img src="assets/logo.png" width="100%" /> </div> Tnlearn is an open source python library. It is based on the symbolic regression algorithm to generate task-based neurons, and then utilizes diverse neurons to build neural networks.     # Quick links - [Quick links](#quick-links) - [Motivation](#motivation) - [Features](#features) - [Overview](#overview) - [Benchmarks](#benchmarks) - [Resource](#resource) - [Dependences](#dependences) - [Install](#install) - [Quick start](#quick-start) - [API documentation](#api-documentation) - [Citation](#citation) - [The Team](#the-team) - [License](#license) # Motivation * **NuronAI inspired** In the past decade, successful networks have primarily used a single type of neurons within novel architectures, yet recent deep learning studies have been inspired by the diversity of human brain neurons, leading to the proposal of new artificial neuron designs. * **Task-Based Neuron Design** Given the human brain's reliance on task-based neurons, can artificial network design shift from focusing on task-based architecture to task-based neuron design? * **Enhanced Representation** Since there are no universally applicable neurons, task-based neurons could enhance feature representation ability within the same structure, due to the intrinsic inductive bias for the task. # Features * Vectorized symbolic regression is employed to find optimal formulas that fit input data. * We parameterize the obtained elementary formula to create learnable parameters, serving as the neuron's aggregation function. # Overview A nice picture describing the structure of tnlearn will be produced here. # Benchmarks We select several advanced machine learning methods for comparison. | Method | Venues | Code link | | :-------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | | XGBoost | [ACM SIGKDD 2016](https://dl.acm.org/doi/abs/10.1145/2939672.2939785) | [Adopt official code](https://github.com/dmlc/xgboost) | | LightGBM | [NeurIPS 2017](https://proceedings.neurips.cc/paper_files/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf) | Implemented by [widedeep](https://github.com/jrzaurin/pytorch-widedeep) | | CatBoost | [Journal of big data](https://link.springer.com/article/10.1186/s40537-020-00369-8) | [Adopt official code](https://github.com/catboost/catboost) | | TabNet | [AAAI 2021](https://ojs.aaai.org/index.php/AAAI/article/view/16826) | Implemented by [widedeep](https://github.com/jrzaurin/pytorch-widedeep) | | Tab Transformer | [arxiv](https://arxiv.org/abs/2012.06678) | [Adopt official code](https://github.com/lucidrains/tab-transformer-pytorch) | | FT-Transformer | [NeurIPS 2021](https://proceedings.neurips.cc/paper_files/paper/2021/hash/9d86d83f925f2149e9edb0ac3b49229c-Abstract.html) | Implemented by [widedeep](https://github.com/jrzaurin/pytorch-widedeep) | | DANETs | [AAAI 2022](https://ojs.aaai.org/index.php/AAAI/article/view/20309) | [Adopt official code](https://github.com/whatashot/danet) | We test multiple advanced machine learning methods on two sets of real-world data. The test results (MSE) are shown in the following table: | Method | [Particle collision](https://www.kaggle.com/datasets/fedesoriano/cern-electron-collision-data) | [Asteroid prediction](https://www.kaggle.com/datasets/basu369victor/prediction-of-<br/>asteroid-diameter) | | :----------------: | :
Excerpt of 11,650 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c49966ad9335f554, llm:Repository topics and description: 'deep-learning-algorithms, genetic-programming, task-based-neurons, vectorized-symbolic-regression' and description: 'A Python package that uses task-based neurons to build neural networks.'
matched fp:c49966ad9335f554, llm:Repository topics and description: 'deep-learning-algorithms, genetic-programming, task-based-neurons, vectorized-symbolic-regression' and description: 'A Python package that uses task-based neurons to build neural networks.'
matched fp:c49966ad9335f554, llm:Repository topics and description: 'deep-learning-algorithms, genetic-programming, task-based-neurons, vectorized-symbolic-regression' and description: 'A Python package that uses task-based neurons to build neural networks.'