CRISP: A Framework for Clause-Reconstructed Interpretable NeuroSymbolic Propositions
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- Understanding intermediate layers using linear classifier probes
- The Tsetlin Machine -- A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- Deep Learning for Classical Japanese Literature
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks