ASCEND
BY NTHRYS

NTHRYS › PhD Assistance › Artificial Intelligence

Artificial Intelligence

Field
▾
Category
▾

Artificial Intelligence

Select a category to explore research frontiers

Loading categories...

Research Frontiers in Explainable AI and Interpretability Methods

Development of techniques to make deep neural networks and complex AI models transparent, understandable, and auditable for human decision makers.

Causal Attribution in Deep Neural Networks
Counterfactual Explanations for Adversarial Robustness
Mechanistic Interpretability of Transformer Attention
Symbolic Grounding in Black-Box Model Decisions
Temporal Coherence in Sequential Model Explanations
Concept-Based Interpretability Beyond Feature Attribution
Faithfulness Verification in Post-Hoc Explanations
Interpretability Under Distribution Shift
Neural Circuit Discovery in Learned Representations
Explanation Robustness Against Model Perturbations

All Artificial Intelligence PhD categories