conftrace_

neural network interpretability

114 papers

Explore in graph

Co-occurring keywords

neural network (6616) feature attribution (280) deep neural network (1803) representation learning (6206) large language model (13587) attribution method (79) image classification (1944) convolutional neural network (4226) model explanation (155) model analysis (56)

Papers

Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training CVPR 2024
Deep Neural Networks via Complex Network Theory: A Perspective IJCAI 2024
Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract) AAAI 2024
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models NIPS 2024
Measuring Per-Unit Interpretability at Scale Without Humans NIPS 2024
Pixel-Grounded Prototypical Part Networks WACV 2024
Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images NIPS 2023
Cardinality-Minimal Explanations for Monotonic Neural Networks IJCAI 2023
CRAFT: Concept Recursive Activation FacTorization for Explainability CVPR 2023
Negative Flux Aggregation to Estimate Feature Attributions IJCAI 2023
MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope ICCV 2023
SEAT: Stable and Explainable Attention AAAI 2023
Experimental Observations of the Topology of Convolutional Neural Network Activations AAAI 2023
SmoothHess: ReLU Network Feature Interactions via Stein's Lemma NIPS 2023
Towards a fuller understanding of neurons with Clustered Compositional Explanations NIPS 2023
Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation ACML 2023
Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement NIPS 2023
Rigorously Assessing Natural Language Explanations of Neurons EMNLP 2023
Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization NIPS 2023
Formal Explanations of Neural Network Policies for Planning IJCAI 2023
Disentangling Transformer Language Models as Superposed Topic Models EMNLP 2023
Latent Inspector: An Interactive Tool for Probing Neural Network Behaviors Through Arbitrary Latent Activation IJCAI 2023
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods ACL 2023
Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution EMNLP 2023
Cones: Concept Neurons in Diffusion Models for Customized Generation ICML 2023