mlsanityData to 14 Oct 2026

Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks

arXiv 2607.09399 ↗First posted 10 Jul 2026cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

We introduce a novel method for both partial and full optimization of the connections in deep differentiable logic gate networks (LGNs) and lookup table networks (LUTNs). Our training method utilizes a probability distribution over a set of connections per gate/lookup table (LUT) input pin, selecting the connection with highest merit, all whilst the optimal gate types or LUT-entries are learned in parallel. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST Handwritten Digits and Fashion-MNIST benchmarks, while requiring only a fraction of the number of logic gates. We achieve 98.92% on the MNIST dataset with two layers of 8000 gates. With only one layer of 8000 gates, we obtain 98.45%, showing that our method requires almost 50 times fewer gates compared to fixed-connection LGNs. Training stability up to ten layers has been ensured by employing a high learning rate, straight-through estimators and trimming constant-output gate types. Additionally, we present a LUT neuron description that enables stable training with backpropagation, tested up to 6-layer deep networks. The model requires four times fewer trainable parameters and still achieves a higher accuracy compared to the fixed-connection LGN training algorithm. Our connection-training algorithm also works well for the LUTNs, achieving an accuracy of 98.88% for two layers of 2000 6-input LUTs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 15 of its 23 references that are in the map. First posted on arXiv 10 Jul 2026.

Builds on

15 of 23 references.

References · 15

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  2. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  3. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  4. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  5. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 177
  6. 2022Compute Trends Across Three Eras of Machine Learningcited by 163
  7. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  8. 2020LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput Applicationscited by 57
  9. 2017STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognitioncited by 46
  10. 2021Q-SpiNN: A Framework for Quantizing Spiking Neural Networkscited by 37
  11. 2023PolyLUT: Learning Piecewise Polynomials for Ultra-Low Latency FPGA LUT-based Inferencecited by 30
  12. 2024NeuraLUT: Hiding Neural Network Density in Boolean Synthesizable Functionscited by 21
3 more
  1. 2025WARP-LUTs -- Walsh-Assisted Relaxation for Probabilistic Look Up Tablescited by 6
  2. 2016TrueHappiness: Neuromorphic Emotion Recognition on TrueNorthcited by 5
  3. 2026Inter-patient ECG Arrhythmia Classification with LGNs and LUTNscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026On the Depth Scalability of Logic Gate Networkscited by 0
  2. 2026DiffLUT-Net: Differentiable Training of FPGA LUT Networks with Learnable Connectivitycited by 0