# TNLearn: An Open Source Python Package for Task-based Neurons

arXiv: https://arxiv.org/abs/2609.27564 · HTML: https://mlsanity.com/paper/2609.27564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Deep Polynomial Neural Networks](https://mlsanity.com/paper/2006.13026/) (2020)
- [Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEs](https://mlsanity.com/paper/2101.08366/) (2021)
- [Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising](https://mlsanity.com/paper/1901.05593/) (2019)
- [Exhaustive Symbolic Regression](https://mlsanity.com/paper/2211.11461/) (2022)
- [DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience](https://mlsanity.com/paper/2506.04282/) (2025)
- [Augmenting Deep Classifiers with Polynomial Neural Networks](https://mlsanity.com/paper/2104.07916/) (2021)
- [QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Exploration](https://mlsanity.com/paper/2204.01701/) (2022)
- [On a Sparse Shortcut Topology of Artificial Neural Networks](https://mlsanity.com/paper/1811.09003/) (2018)
- [A New Type of Neurons for Machine Learning](https://mlsanity.com/paper/1704.08362/) (2017)
- [OpenML: An R Package to Connect to the Machine Learning Platform OpenML](https://mlsanity.com/paper/1701.01293/) (2017)
- [One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networks](https://mlsanity.com/paper/2303.06316/) (2023)
- [Enabling Population-Level Parallelism in Tree-Based Genetic Programming for GPU Acceleration](https://mlsanity.com/paper/2501.17168/) (2025)
- [No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks](https://mlsanity.com/paper/2405.02369/) (2024)
- [QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation](https://mlsanity.com/paper/2405.03192/) (2024)

## Abstract (arXiv)

The brain does not rely on a single type of neuron to perform all kinds of tasks; instead, it designs different neurons for different tasks. The concept of task-based neurons represents a paradigm shift compared to task-based architectures. It argues that solving a specific problem requires customized neurons, as task-based neurons capture useful prior knowledge from task-related data. To facilitate the use of task-based neurons in scientific research and industrial applications, we introduce TNLearn, an open-source Python package that provides automated construction of task-based neurons and networks, enabling smooth training of task-based networks. Comprehensive documentation, including technical exposition, API reference, and representative examples, is available online. TNLearn is open-sourced at https://github.com/NewT123-WM/tnlearn and has become a PyTorch ecosystem project.