mlsanityData to 14 Oct 2026

A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables

arXiv 2208.08609 ↗First posted 18 Aug 2022cs.AI cs.FL cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose Truth Table net (TTnet), a novel Convolutional Neural Network (CNN) architecture that addresses, by design, the open challenges of interpretability, formal verification, and logic gate conversion. TTnet is built using CNNs' filters that are equivalent to tractable truth tables and that we call Learning Truth Table (LTT) blocks. The dual form of LTT blocks allows the truth tables to be easily trained with gradient descent and makes these CNNs easy to interpret, verify and infer. Specifically, TTnet is a deep CNN model that can be automatically represented, after post-training transformation, as a sum of Boolean decision trees, or as a sum of Disjunctive/Conjunctive Normal Form (DNF/CNF) formulas, or as a compact Boolean logic circuit. We demonstrate the effectiveness and scalability of TTnet on multiple datasets, showing comparable interpretability to decision trees, fast complete/sound formal verification, and scalable logic gate representation, all compared to state-of-the-art methods. We believe this work represents a step towards making CNNs more transparent and trustworthy for real-world critical applications.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 53 of its 116 references that are in the map. First posted on arXiv 18 Aug 2022.

Builds on

53 of 116 references.

References · 53

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  10. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  11. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  12. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
38 more
  1. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  2. 2017Self-Normalizing Neural Networkscited by 598
  3. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  4. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  5. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 527
  6. 2019On Evaluating Adversarial Robustnesscited by 447
  7. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
  8. 2018Certified Defenses against Adversarial Examplescited by 306
  9. 2020A Survey on Neural Network Interpretabilitycited by 291
  10. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  11. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  12. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 235
  13. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  14. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 187
  15. 2016A guide to convolution arithmetic for deep learningcited by 185
  16. 2018Scaling provable adversarial defensescited by 143
  17. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 127
  18. 2017Maximum Resilience of Artificial Neural Networkscited by 97
  19. 2018Boolean Decision Rules via Column Generationcited by 80
  20. 2017Verifying Properties of Binarized Deep Neural Networkscited by 79
  21. 2021PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximationscited by 77
  22. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  23. 2018Training for Faster Adversarial Robustness Verification via Inducing ReLU Stabilitycited by 67
  24. 2019Quantitative Verification of Neural Networks And its Security Applicationscited by 56
  25. 2021Shapley values for feature selection: The good, the bad, and the axiomscited by 54
  26. 2017Learning Certifiably Optimal Rule Lists for Categorical Datacited by 50
  27. 2018Training verified learners with learned verifierscited by 50
  28. 2021Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neuronscited by 40
  29. 2021Scalable Rule-Based Representation Learning for Interpretable Classificationcited by 40
  30. 2019Generalized Linear Rule Modelscited by 36
  31. 2020Exploiting Verified Neural Networks via Floating Point Numerical Errorcited by 35
  32. 2020On Tractable Representations of Binary Neural Networkscited by 34
  33. 2020Efficient Exact Verification of Binarized Neural Networkscited by 33
  34. 2019LUTNet: Rethinking Inference in FPGA Soft Logiccited by 28
  35. 2019Provably Robust Boosted Decision Stumps and Trees against Adversarial Attackscited by 26
  36. 2022Scalable Verification of GNN-based Job Schedulerscited by 19
  37. 2021BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networkscited by 17
  38. 2022Learning Interpretable Decision Rule Sets: A Submodular Optimization Approachcited by 13

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Convolutional Differentiable Logic Gate Networkscited by 37
  2. 2025eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networkscited by 3
  3. 2026Learning Compact Boolean Networkscited by 1
  4. 2026Overcoming Kernel Redundancy for Scaling Logic Gate Networkscited by 0