conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

GlanceNets: Interpretable, Leak-proof Concept-based Models NIPS 2022
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off NIPS 2022
Exploring the Latent Space of Autoencoders with Interventional Assays NIPS 2022
FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation NIPS 2022
Tractable Function-Space Variational Inference in Bayesian Neural Networks NIPS 2022
Noise Attention Learning: Enhancing Noise Robustness by Gradient Scaling NIPS 2022
Addressing Leakage in Concept Bottleneck Models NIPS 2022
Extracting computational mechanisms from neural data using low-rank RNNs NIPS 2022
Towards Improving Faithfulness in Abstractive Summarization NIPS 2022
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models NIPS 2022
LieGG: Studying Learned Lie Group Generators NIPS 2022
Learning Recourse on Instance Environment to Enhance Prediction Accuracy NIPS 2022
Linear tree shap NIPS 2022
CLEAR: Generative Counterfactual Explanations on Graphs NIPS 2022
Distinguishing Learning Rules with Brain Machine Interfaces NIPS 2022
Evaluation beyond Task Performance: Analyzing Concepts in AlphaZero in Hex NIPS 2022
Distilled Gradient Aggregation: Purify Features for Input Attribution in the Deep Neural Network NIPS 2022
DARE: Disentanglement-Augmented Rationale Extraction NIPS 2022
ProtoX: Explaining a Reinforcement Learning Agent via Prototyping NIPS 2022
Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning NIPS 2022
Explaining Preferences with Shapley Values NIPS 2022
Structuring Uncertainty for Fine-Grained Sampling in Stochastic Segmentation Networks NIPS 2022
On Computing Probabilistic Explanations for Decision Trees NIPS 2022
Semantic Probabilistic Layers for Neuro-Symbolic Learning NIPS 2022
Tsetlin Machine for Solving Contextual Bandit Problems NIPS 2022