# Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data

arXiv: https://arxiv.org/abs/2409.07942 · HTML: https://mlsanity.com/paper/2409.07942/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 12 Sep 2024.

## Builds on (most cited first, 21 of 21)

- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2101.12072/) (2021)
- [Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning](https://mlsanity.com/paper/1902.03932/) (2019)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [Spatial-Adaptive Network for Single Image Denoising](https://mlsanity.com/paper/2001.10291/) (2020)
- [Challenges in Markov chain Monte Carlo for Bayesian neural networks](https://mlsanity.com/paper/1910.06539/) (2019)
- [Is MC Dropout Bayesian?](https://mlsanity.com/paper/2110.04286/) (2021)
- [Variational AutoEncoder For Regression: Application to Brain Aging Analysis](https://mlsanity.com/paper/1904.05948/) (2019)
- [MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network](https://mlsanity.com/paper/2304.01598/) (2023)
- [Active Learning Using Uncertainty Information](https://mlsanity.com/paper/1702.08540/) (2017)
- [PDE-LEARN: Using Deep Learning to Discover Partial Differential Equations from Noisy, Limited Data](https://mlsanity.com/paper/2212.04971/) (2022)
- [How to Evaluate Uncertainty Estimates in Machine Learning for Regression?](https://mlsanity.com/paper/2106.03395/) (2021)
- [Applications of Artificial Neural Networks in Microorganism Image Analysis: A Comprehensive Review from Conventional Multilayer Perceptron to Popular Convolutional Neural Network and Potential Visual Transformer](https://mlsanity.com/paper/2108.00358/) (2021)
- [Improving evidential deep learning via multi-task learning](https://mlsanity.com/paper/2112.09368/) (2021)
- [Uncertainty Quantification by Ensemble Learning for Computational Optical Form Measurements](https://mlsanity.com/paper/2103.01259/) (2021)
- [Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression](https://mlsanity.com/paper/2003.10804/) (2020)
- [Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation](https://mlsanity.com/paper/2209.11679/) (2022)

## Abstract (arXiv)

Uncertainty estimation is crucial in scientific data for machine learning. Current uncertainty estimation methods mainly focus on the model's inherent uncertainty, while neglecting the explicit modeling of noise in the data. Furthermore, noise estimation methods typically rely on temporal or spatial dependencies, which can pose a significant challenge in structured scientific data where such dependencies among samples are often absent. To address these challenges in scientific research, we propose the Taylor-Sensus Network (TSNet). TSNet innovatively uses a Taylor series expansion to model complex, heteroscedastic noise and proposes a deep Taylor block for aware noise distribution. TSNet includes a noise-aware contrastive learning module and a data density perception module for aleatoric and epistemic uncertainty. Additionally, an uncertainty combination operator is used to integrate these uncertainties, and the network is trained using a novel heteroscedastic mean square error loss. TSNet demonstrates superior performance over mainstream and state-of-the-art methods in experiments, highlighting its potential in scientific research and noise resistance. It will be open-source to facilitate the community of "AI for Science".