Explainable Artificial Intelligence (XAI)

This paper introduces Scrambler networks, a method for interpreting sequence-based neural networks by learning stochastic masks to identify salient sequence positions and explain model predictions.

This paper introduces an activation maximization method for electrophysiology classifiers, showing it can identify spectral patterns in EEG sleep stages and reveal potential reliance on artifacts for awake classification.

This paper introduces a local ablation method to explain multimodal classifiers, showing EEG's importance in sleep staging and identifying demographic effects on classification.

This paper introduces a local spectral explainability method to analyze deep learning classifiers trained on raw EEG data for sleep stage classification, showing varying frequency band importance over time and within sleep stages.

This paper introduces Global Importance Analysis (GIA), a method to quantify the effect size of genomic features in deep neural networks, demonstrating its application in predicting RNA-protein interactions.

The paper introduces GLRP, a method to explain Graph-CNN decisions in breast cancer metastasis prediction, identifying patient-specific molecular subnetworks that align with clinical knowledge.

This study shows that using exponential activations in the first layer of CNNs improves the interpretability and robustness of genomic sequence motif representations in both synthetic and real DNA data.

The paper investigates whether accurate model interpretation can be achieved through good prediction in flexible models and proposes a method to identify correctly interpreted models.

The paper introduces a method to interpret machine-learning classifiers by analyzing how noise and reverse correlation affect classification decisions across various data types and models.

The paper critiques protein family classification models by identifying sufficient input subsets to understand their decision-making criteria.

gkmexplain provides a fast and accurate method to interpret gkm-SVM models of regulatory DNA sequences, outperforming existing methods in identifying predictive patterns and mutation impact scores.

The paper develops interpretable genotype-to-phenotype classifiers with performance guarantees, validated on antimicrobial resistance prediction across 12 species and 56 antibiotics.