Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers
quant-ph, cs.LG, physics.optics
Submitted: 2026-11-01
Updated: 2026-11-05
Code: https://github.com/stein-research/seeing-why
Terminology
Sources
- Axiomatic Attribution for Deep Networks
- A Unified Approach to Interpreting Model Predictions
- eXplainable AI for Quantum Machine Learning
- HattriQ: Designing Integrated Gradients for Feature Attribution in Quantum Machine Learning
- Explaining Quantum Circuits with Shapley Values: Towards Explainable Quantum Machine Learning
- Opportunities and limitations of explaining quantum machine learning
- Four Axiomatic Characterizations of the Integrated Gradients Attribution Method
- Methodology for replacing indirect measurements with direct measurements
- Training of photonic neural networks through in situ backpropagation
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- PennyLane: Automatic differentiation of hybrid quantum-classical computations
- Quantum computing with Qiskit
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- On Calibration of Modern Neural Networks
- RISE: Randomized Input Sampling for Explanation of Black-box Models
- Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
- Towards better understanding of gradient-based attribution methods for Deep Neural Networks
- A Benchmark for Interpretability Methods in Deep Neural Networks
- Sanity Checks for Saliency Maps
Related papers
- Computational regimes in matrix-product-state-based quantum trajectory simulations
- Toward chemically accurate quantum simulations on quantum hardware: A quantum-HPC hybrid approach
- Transversal surface-code game with reconfigurable qubits
- Fulqrum: a generalized framework for quantum subspace diagonalization
- Flux-Activated Resonant Control of a Bosonic Quantum Memory
- Machine learning the effects of many quantum measurements