mlsanityData to 13 Oct 2026

A Method for Optimizing Connections in Differentiable Logic Gate Networks

arXiv 2507.06173 ↗First posted 8 Jul 2025cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce a novel method for partial optimization of the connections in Deep Differentiable Logic Gate Networks (LGNs). Our training method utilizes a probability distribution over a subset of connections per gate input, selecting the connection with highest merit, after which the gate-types are selected. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST and Fashion-MNIST benchmarks, while requiring only a fraction of the number of logic gates. When training all connections, we demonstrate that 8000 simple logic gates are sufficient to achieve over 98% on the MNIST data set. Additionally, we show that our network has 24 times fewer gates, while performing better on the MNIST data set compared to standard fully connected LGNs. As such, our work shows a pathway towards fully trainable Boolean logic.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 12 of its 17 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

12 of 17 references.

References · 12

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,328
  2. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  3. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 422
  4. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 256
  5. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 176
  6. 2022Compute Trends Across Three Eras of Machine Learningcited by 163
  7. 2022Deep Differentiable Logic Gate Networkscited by 67
  8. 2017STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognitioncited by 45
  9. 2021Q-SpiNN: A Framework for Quantizing Spiking Neural Networkscited by 37
  10. 2024Convolutional Differentiable Logic Gate Networkscited by 37
  11. 2019LUTNet: Rethinking Inference in FPGA Soft Logiccited by 28
  12. 2016TrueHappiness: Neuromorphic Emotion Recognition on TrueNorthcited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025WARP-LUTs -- Walsh-Assisted Relaxation for Probabilistic Look Up Tablescited by 6
  2. 2026WARP Logic Neural Networkscited by 2
  3. 2026Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networkscited by 2
  4. 2025Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Controlcited by 1
  5. 2026Inter-patient ECG Arrhythmia Classification with LGNs and LUTNscited by 1