# Toward Improving fNIRS Classification: A Study on Activation Functions in Deep Neural Architectures

arXiv: https://arxiv.org/abs/2507.11436 · HTML: https://mlsanity.com/paper/2507.11436/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Builds on (most cited first, 6 of 6)

- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark](https://mlsanity.com/paper/2109.14545/) (2021)
- [Deep Learning in fNIRS: A review](https://mlsanity.com/paper/2201.13371/) (2022)
- [AbsoluteNet: A Deep Learning Neural Network to Classify Cerebral Hemodynamic Responses of Auditory Processing](https://mlsanity.com/paper/2506.00039/) (2025)
- [An end-to-end (deep) neural network applied to raw EEG, fNIRs and body motion data for data fusion and BCI classification task without any pre-/post-processing](https://mlsanity.com/paper/1907.09523/) (2019)
- [Accurate Stress Assessment based on functional Near Infrared Spectroscopy using Deep Learning Approach](https://mlsanity.com/paper/2002.06282/) (2020)

## Built on by (most cited first, 2 of 2)

- [Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model](https://mlsanity.com/paper/2511.00443/) (2025)
- [Beyond Gaussian Initializations: Signal Preserving Weight Initialization for Odd-Sigmoid Activations](https://mlsanity.com/paper/2509.23085/) (2025)

## Abstract (arXiv)

Activation functions are critical to the performance of deep neural networks, particularly in domains such as functional near-infrared spectroscopy (fNIRS), where nonlinearity, low signal-to-noise ratio (SNR), and signal variability poses significant challenges to model accuracy. However, the impact of activation functions on deep learning (DL) performance in the fNIRS domain remains underexplored and lacks systematic investigation in the current literature. This study evaluates a range of conventional and field-specific activation functions for fNIRS classification tasks using multiple deep learning architectures, including the domain-specific fNIRSNet, AbsoluteNet, MDNN, and shallowConvNet (as the baseline), all tested on a single dataset recorded during an auditory task. To ensure fair a comparison, all networks were trained and tested using standardized preprocessing and consistent training parameters. The results show that symmetrical activation functions such as Tanh and the Absolute value function Abs(x) can outperform commonly used functions like the Rectified Linear Unit (ReLU), depending on the architecture. Additionally, a focused analysis of the role of symmetry was conducted using a Modified Absolute Function (MAF), with results further supporting the effectiveness of symmetrical activation functions on performance gains. These findings underscore the importance of selecting proper activation functions that align with the signal characteristics of fNIRS data.