# Evaluation of Interpretability for Deep Learning algorithms in EEG Emotion Recognition: A case study in Autism

arXiv: https://arxiv.org/abs/2111.13208 · HTML: https://mlsanity.com/paper/2111.13208/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 81 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Learning how to explain neural networks: PatternNet and PatternAttribution](https://mlsanity.com/paper/1705.05598/) (2017)
- [iNNvestigate neural networks!](https://mlsanity.com/paper/1808.04260/) (2018)
- [Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps](https://mlsanity.com/paper/1902.04893/) (2019)
- [Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications](https://mlsanity.com/paper/2003.07631/) (2020)
- [Interpretable SincNet-based Deep Learning for Emotion Recognition from EEG brain activity](https://mlsanity.com/paper/2107.10790/) (2021)

## Built on by (most cited first, 6 of 6)

- [Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine](https://mlsanity.com/paper/2211.09317/) (2022)
- [Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey](https://mlsanity.com/paper/2307.09615/) (2023)
- [Applications of Explainable artificial intelligence in Earth system science](https://mlsanity.com/paper/2406.11882/) (2024)
- [Neural Memory Decoding with EEG Data and Representation Learning](https://mlsanity.com/paper/2307.13181/) (2023)
- [Deep learning for autism detection using clinical notes: A comparison of transfer learning for a transparent and black-box approach](https://mlsanity.com/paper/2512.06161/) (2025)
- [AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps](https://mlsanity.com/paper/2605.16905/) (2026)

## Abstract (arXiv)

Current models on Explainable Artificial Intelligence (XAI) have shown an evident and quantified lack of reliability for measuring feature-relevance when statistically entangled features are proposed for training deep classifiers. There has been an increase in the application of Deep Learning in clinical trials to predict early diagnosis of neuro-developmental disorders, such as Autism Spectrum Disorder (ASD). However, the inclusion of more reliable saliency-maps to obtain more trustworthy and interpretable metrics using neural activity features is still insufficiently mature for practical applications in diagnostics or clinical trials. Moreover, in ASD research the inclusion of deep classifiers that use neural measures to predict viewed facial emotions is relatively unexplored. Therefore, in this study we propose the evaluation of a Convolutional Neural Network (CNN) for electroencephalography (EEG)-based facial emotion recognition decoding complemented with a novel RemOve-And-Retrain (ROAR) methodology to recover highly relevant features used in the classifier. Specifically, we compare well-known relevance maps such as Layer-Wise Relevance Propagation (LRP), PatternNet, Pattern-Attribution, and Smooth-Grad Squared. This study is the first to consolidate a more transparent feature-relevance calculation for a successful EEG-based facial emotion recognition using a within-subject-trained CNN in typically-developed and ASD individuals.