Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

Nov-17-2025, 03:03:07 GMT–Neural Information Processing Systems

We present a new algorithm to generate minimal, stable, and symbolic corrections to an input that will cause a neural network with ReLU activations to change its output.

artificial intelligence, correction, machine learning, (18 more...)

Neural Information Processing Systems

Nov-17-2025, 03:03:07 GMT

Conferences PDF

Add feedback

Country:
- Europe
  - Spain > Catalonia
    - Barcelona Province > Barcelona (0.04)
  - Switzerland > Zürich
    - Zürich (0.14)
- North America
  - Canada > Quebec
    - Montreal (0.04)
  - United States
    - Arizona > Maricopa County
      - Scottsdale (0.04)
    - California
      - Los Angeles County > Long Beach (0.04)
      - San Francisco County > San Francisco (0.14)
    - Louisiana > Orleans Parish
      - New Orleans (0.04)
    - Massachusetts
      - Middlesex County > Cambridge (0.04)
      - Suffolk County > Boston (0.04)
    - Nebraska (0.04)
- Oceania > Australia
  - New South Wales > Sydney (0.04)

Industry:
- Banking & Finance > Loans (0.48)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Learning Graphical Models > Undirected Networks
      - Markov Models (0.46)
    - Neural Networks > Deep Learning (0.68)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections
Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

Similar Docs Excel Report more

Title	Similarity	Source
None found