Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks

• URL: http://arxiv.org/abs/2607.09399v1
• Date: Fri, 10 Jul 2026 13:24:26 GMT
• Title: Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks
• Abstract summary: We introduce a novel method for partial and full optimization of connections in differentiable logic gate networks (LGNs) and lookup table networks (LUTNs)<n>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.<n>We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST Handwritten Digits and Fashion-MNIST benchmarks.
• Score: 0.33554367023486936
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DiffLUT-Net: Differentiable Training of FPGA LUT Networks with Learnable Connectivity [7.054660214035757]
  We present DiffLUT-Net, an FPGA-native network connected by six-input LUTs that are trained from scratch.<n>After training, the truth tables and connections are discretized, unused logic can be pruned, and the network is exported directly as Verilog.
  arXiv  Detail & Related papers  (2026-09-08T15:00:50Z)
• Inter-patient ECG Arrhythmia Classification with LGNs and LUTNs [0.5856479799932673]
  LGNs and LUTNs are demonstrated to be suitable for the automatic classification of electrocardiograms (ECGs) using the inter-patient paradigm.<n>The methods are benchmarked using the MIT-BIH arrhythmia data set, achieving up to 94.28% accuracy and a $j$ index of 0.683 on a four-class classification problem.
  arXiv  Detail & Related papers  (2026-01-16T16:55:36Z)
• LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment [0.0]
  We show how to train networks of binary logic gates using gradient-based methods.<n>We show how to substantially reduce the number of logic gates required to fit a particular dataset.<n>For our largest architecture with 256,000 gates, LILogicNet achieves 60.98% test accuracy on CIFAR-10.
  arXiv  Detail & Related papers  (2025-11-15T19:44:37Z)
• What Layers When: Learning to Skip Compute in LLMs with Residual Gates [66.23658560048241]
  GateSkip is a residual-stream gating mechanism that enables token-wise layer skipping in decoder-only LMs.<n>Each Attention/MLP branch is equipped with a sigmoid-linear gate that condenses the branch's output before it re-enters the residual stream.
  arXiv  Detail & Related papers  (2025-10-13T16:31:50Z)
• Above 99.9% Fidelity Single-Qubit Gates, Two-Qubit Gates, and Readout in a Single Superconducting Quantum Device [58.154405222706146]
  tuning of qubit-coupler coupling strengths in a superconducting circuit with two transmon qubits coupled via a tunable coupler enables high-fidelity single- and two-qubit gates.<n>We achieve a 40h-averaged CZ gate fidelity of 99.93%, simultaneous single-qubit gate fidelities of 99.98%, and readout fidelities over 99.94% in a single device.
  arXiv  Detail & Related papers  (2025-08-22T14:49:47Z)
• A Method for Optimizing Connections in Differentiable Logic Gate Networks [0.48212500317840945]
  We introduce a novel method for partial optimization of the connections in Deep Differentiable Logic Gate Networks (LGNs)<n>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.<n>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.
  arXiv  Detail & Related papers  (2025-07-08T16:53:39Z)
• SparseLUT: Sparse Connectivity Optimization for Lookup Table-based Deep Neural Networks [0.0]
  This paper introduces SparseLUT, a connectivity-centric training technique tailored for LUT-based deep neural networks (DNNs)<n> Experimental results show consistent accuracy improvements across benchmarks, including up to a 2.13% increase on MNIST.<n>This is done without any hardware overhead and achieves state-of-the-art results for LUT-based DNNs.
  arXiv  Detail & Related papers  (2025-03-17T05:21:54Z)
• Convolutional Differentiable Logic Gate Networks [68.74313756770123]
  We propose an approach for learning logic gate networks directly via a differentiable relaxation. We build on this idea, extending it by deep logic gate tree convolutions and logical OR pooling. On CIFAR-10, we achieve an accuracy of 86.29% using only 61 million logic gates, which improves over the SOTA while being 29x smaller.
  arXiv  Detail & Related papers  (2024-11-07T14:12:00Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• NeuraLUT: Hiding Neural Network Density in Boolean Synthesizable Functions [2.7086888205833968]
  Field-Programmable Gate Array (FPGA) accelerators have proven successful in handling latency- and resource-critical deep neural network (DNN) inference tasks. We propose relaxing the boundaries of neurons and mapping entire sub-networks to a single LUT. We validate our proposed method on a known latency-critical task, jet substructure tagging, and on the classical computer vision task, digit classification using MNIST.
  arXiv  Detail & Related papers  (2024-02-29T16:10:21Z)
• Hybrid-Task Meta-Learning: A GNN Approach for Scalable and Transferable Bandwidth Allocation [50.96751567777229]
  We develop a deep learning-based bandwidth allocation policy that is scalable with the number of users and transferable to different communication scenarios.<n>To support scalability, the bandwidth allocation policy is represented by a graph neural network (GNN)<n>We develop a hybrid-task meta-learning (HML) algorithm that trains the initial parameters of the GNN with different communication scenarios.
  arXiv  Detail & Related papers  (2023-12-23T04:25:12Z)
• T-GAE: Transferable Graph Autoencoder for Network Alignment [79.89704126746204]
  T-GAE is a graph autoencoder framework that leverages transferability and stability of GNNs to achieve efficient network alignment without retraining. Our experiments demonstrate that T-GAE outperforms the state-of-the-art optimization method and the best GNN approach by up to 38.7% and 50.8%, respectively.
  arXiv  Detail & Related papers  (2023-10-05T02:58:29Z)
• Convolutional Networks with Dense Connectivity [59.30634544498946]
  We introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks.
  arXiv  Detail & Related papers  (2020-01-08T06:54:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.