aaai 2021 论文列表
Proceedings of the Workshop on Artificial Intelligence Safety 2021 (SafeAI 2021) co-located with the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021), Virtual, February 8, 2021.
|
Classification Confidence Scores with Point-wise Guarantees.
Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data.
Neural Criticality: Validation of Convolutional Neural Networks.
AI-Blueprint for Deep Neural Networks.
Time for AI (Ethics) Maturity Model Is Now.
Negative Side Effects and AI Agent Indicators: Experiments in SafeLife.
Runtime Decision Making Under Uncertainty in Autonomous Vehicles.
On the Use of Available Testing Methods for Verification & Validation of AI-based Software and Systems.
Overestimation Learning with Guarantees.
Towards an Ontological Framework for Environmental Survey Hazard Analysis of Autonomous Systems.
Challenges for Using Impact Regularizers to Avoid Negative Side Effects.
Deep CPT-RL: Imparting Human-Like Risk Sensitivity to Artificial Agents.
Performance of Bounded-Rational Agents With the Ability to Self-Modify.
What criminal and civil law tells us about Safe RL techniques to generate law-abiding behaviour.
DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation.
Multi-Modal Generative Adversarial Networks Make Realistic and Diverse but Untrustworthy Predictions When Applied to Ill-posed Problems.
Adversarial Robustness for Face Recognition: How to Introduce Ensemble Diversity among Feature Extractors?
A Hybrid-AI Approach for Competence Assessment of Automated Driving functions.
Safety Properties of Inductive Logic Programming.
The Utility of Neural Network Test Coverage Measures.
From Black-box to White-box: Examining Confidence Calibration under different Conditions.
An Evaluation of "Crash Prediction Networks" (CPN) for Autonomous Driving Scenarios in CARLA Simulator.
Feature Space Singularity for Out-of-Distribution Detection.
