# Interpretable Deep Neural Networks for Single-Trial EEG Classification

arXiv: https://arxiv.org/abs/1604.08201 · HTML: https://mlsanity.com/paper/1604.08201/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2016.

## Built on by (most cited first, 24 of 24)

- [Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces](https://mlsanity.com/paper/2212.14855/) (2022)
- [Explainable AI for Time Series via Virtual Inspection Layers](https://mlsanity.com/paper/2303.06365/) (2023)
- [Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteria](https://mlsanity.com/paper/2211.01738/) (2022)
- [Interpretable and Robust AI in EEG Systems: A Survey](https://mlsanity.com/paper/2304.10755/) (2023)
- [Towards Best Practice of Interpreting Deep Learning Models for EEG-based Brain Computer Interfaces](https://mlsanity.com/paper/2202.06948/) (2022)
- [A Simple Self-Supervised ECG Representation Learning Method via Manipulated Temporal-Spatial Reverse Detection](https://mlsanity.com/paper/2202.12458/) (2022)
- [EEG Emotion Copilot: Optimizing Lightweight LLMs for Emotional EEG Interpretation with Assisted Medical Record Generation](https://mlsanity.com/paper/2410.00166/) (2024)
- [Explainability: Relevance based Dynamic Deep Learning Algorithm for Fault Detection and Diagnosis in Chemical Processes](https://mlsanity.com/paper/2103.12222/) (2021)
- [Explainable artificial intelligence approaches for brain-computer interfaces: a review and design space](https://mlsanity.com/paper/2312.13033/) (2023)
- [Interpretable Deep Learning for the Remote Characterisation of Ambulation in Multiple Sclerosis using Smartphones](https://mlsanity.com/paper/2103.09171/) (2021)
- [FATE in AI: Towards Algorithmic Inclusivity and Accessibility](https://mlsanity.com/paper/2301.01590/) (2023)
- [Deep comparisons of Neural Networks from the EEGNet family](https://mlsanity.com/paper/2302.08797/) (2023)
- [Core-set Selection Using Metrics-based Explanations (CSUME) for multiclass ECG](https://mlsanity.com/paper/2205.14508/) (2022)
- [Counterfactual Explanation and Instance-Generation using Cycle-Consistent Generative Adversarial Networks](https://mlsanity.com/paper/2301.08939/) (2023)
- [From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP](https://mlsanity.com/paper/2605.11885/) (2026)
- [Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data](https://mlsanity.com/paper/2109.10895/) (2021)
- [Deep Learning for Size and Microscope Feature Extraction and Classification in Oral Cancer: Enhanced Convolution Neural Network](https://mlsanity.com/paper/2208.07855/) (2022)
- [FingerFlex: Inferring Finger Trajectories from ECoG signals](https://mlsanity.com/paper/2211.01960/) (2022)
- [An Interpretable and Attention-based Method for Gaze Estimation Using Electroencephalography](https://mlsanity.com/paper/2308.05768/) (2023)
- [Methodological Explainability Evaluation of an Interpretable Deep Learning Model for Post-Hepatectomy Liver Failure Prediction Incorporating Counterfactual Explanations and Layerwise Relevance Propagation: A Prospective In Silico Trial](https://mlsanity.com/paper/2408.03771/) (2024)
- [The Role of Explainable AI in Revolutionizing Human Health Monitoring: A Review](https://mlsanity.com/paper/2409.07347/) (2024)
- [From Epilepsy Seizures Classification to Detection: A Deep Learning-based Approach for Raw EEG Signals](https://mlsanity.com/paper/2410.03385/) (2024)
- [EEG Decoding Using CNN and LSTM Network](https://mlsanity.com/paper/2608.13285/) (2026)
- [EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models](https://mlsanity.com/paper/2609.15687/) (2026)

## Abstract (arXiv)

Background: In cognitive neuroscience the potential of Deep Neural Networks (DNNs) for solving complex classification tasks is yet to be fully exploited. The most limiting factor is that DNNs as notorious 'black boxes' do not provide insight into neurophysiological phenomena underlying a decision. Layer-wise Relevance Propagation (LRP) has been introduced as a novel method to explain individual network decisions. New Method: We propose the application of DNNs with LRP for the first time for EEG data analysis. Through LRP the single-trial DNN decisions are transformed into heatmaps indicating each data point's relevance for the outcome of the decision. Results: DNN achieves classification accuracies comparable to those of CSP-LDA. In subjects with low performance subject-to-subject transfer of trained DNNs can improve the results. The single-trial LRP heatmaps reveal neurophysiologically plausible patterns, resembling CSP-derived scalp maps. Critically, while CSP patterns represent class-wise aggregated information, LRP heatmaps pinpoint neural patterns to single time points in single trials. Comparison with Existing Method(s): We compare the classification performance of DNNs to that of linear CSP-LDA on two data sets related to motor-imaginery BCI. Conclusion: We have demonstrated that DNN is a powerful non-linear tool for EEG analysis. With LRP a new quality of high-resolution assessment of neural activity can be reached. LRP is a potential remedy for the lack of interpretability of DNNs that has limited their utility in neuroscientific applications. The extreme specificity of the LRP-derived heatmaps opens up new avenues for investigating neural activity underlying complex perception or decision-related processes.