20 results for “interpretable deep learning”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper proposes a method to approximate the behavior of attention heads in transformer language models with executable programs.
This paper proposes an interpretable framework for singing emotion recognition using singing-specific descriptors.
This paper integrates unsupervised dictionary learning as a post-hoc interpretability module in end-to-end driving models to extract semantically meaningful concepts and improve driving performance.
This paper proposes a joint model for learning textual representations that are both semantically meaningful and aligned with an external response.
The paper proposes the Distilled Explanation Model (DEM), a novel glass-box framework that achieves high-accuracy, clinically interpretable anomaly detection in physiological sensor data by distilling…
This paper demonstrates that Concept Bottleneck Models (CBMs), despite their interpretability, are highly vulnerable to targeted adversarial attacks that manipulate semantic concepts, and proposes SPE…
This paper introduces the Standard Interpretable Model (SIM), a general theory for designing interpretable AI methods.
Leon Bergen, Usha Bhalla, Sidharth Baskaran, Max Loeffler +13 more
This paper introduces a data-centric post-training pipeline to inspect and shape model behavior by making latent concepts explicit for fine-grained user feedback.
Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey +22 more
The paper demonstrates that sparse autoencoders can successfully extract a large set of interpretable, causally influential features from the production-scale Claude 3 Sonnet language model.
The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…
The paper proposes an explainable attention-based LSTM framework to achieve early and reliable detection of advanced, AI-assisted ransomware by analyzing file system behavioral sequences.
This paper investigates deep learning from a physics-informed perspective, examining its key features and surprises.
Kiarash Rezaei, Omran Ayoub, Sebastian Troia, Francesco Lelli +2 more
This paper presents a framework to generate human-understandable natural language explanations for AI/ML models.