Search Results for author:
Found 6 papers, 3 papers with code
Hardness of Deceptive Certificate Selection
A prover selects a certificate from the datapoint and sends it to a verifier who decides the class.
Interpretability Guarantees with Merlin-Arthur Classifiers
We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks.
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
Given only a standard classifier function, it is unclear how partial input should be realised.
A Complete Characterisation of ReLU-Invariant Distributions
We prove that no invariant parametrised family of distributions can exist unless at least one of the following three restrictions holds: First, the network layers have a width of one, which is unreasonable for practical neural networks.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
A Rate-Distortion Framework for Explaining Neural Network Decisions
We formalise the widespread idea of interpreting neural network decisions as an explicit optimisation problem in a rate-distortion framework.
Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior.
