Quantum-Inspired Hybrid Neural Networks for Neural Decoding: A Controlled Ablation Study of Learnable Quantum Sidecar Integration

• URL: http://arxiv.org/abs/2608.22475v1
• Date: Sun, 23 Aug 2026 15:55:43 GMT
• Title: Quantum-Inspired Hybrid Neural Networks for Neural Decoding: A Controlled Ablation Study of Learnable Quantum Sidecar Integration
• Abstract summary: We study parameterized quantum circuits (PQCs) integrated as residual sidecar modules within a ResNet-50 backbone for neural population decoding.<n>We compare four model variants: baseline, quantum sidecar with frozen input projection, quantum sidecar with backbone-gradient-trained projection, and a measurement-guided variant that aligns angle encodings with circuit measurement outcomes.
• Score: 5.2726003549534655
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study parameterized quantum circuits (PQCs) integrated as residual sidecar modules within a ResNet-50 backbone for 31-class neural population decoding---imagined handwriting classification from multi-neuron spike rasters. Under strictly controlled conditions (fixed data splits, seeds, and optimizer), we compare four model variants: baseline, quantum sidecar with frozen input projection, quantum sidecar with backbone-gradient-trained projection, and a measurement-guided variant that aligns angle encodings with circuit measurement outcomes. The backbone-gradient variant improves accuracy in 3/4 seeds (+0.19% mean, 95% CI [-1.10%, +1.48%]) and consistently reduces Linear CKA similarity to baseline features ($Δ=-0.025$, 4/4 seeds), indicating genuine structural reorganization of representations. A nine-variant ablation identifies simple shallow architectures as the most effective and reproducible configuration. Measurement-guided training consistently improves representation geometry without reducing accuracy. All results use noiseless statevector simulation on 4 qubits, a regime chosen to reflect the practical constraints of current near-term superconducting hardware; no quantum computational advantage over classical methods is claimed.

Related papers

• Classical and Hybrid Quantum Machine Learning for Trigger-Like Event Selection on CMS Open Data: An Eight-Qubit, PCA-Constrained Benchmark [0.9106818059692908]
  Event triggering sits at the heart of high-energy physics, where rare events of interest must be retained.<n>This work compares four classical machine learning models, namely a support vector machine, an artificial neural network, a convolutional network and a long short-term memory network.<n>Four hybrid quantum counterparts, on a trigger-like binary classification task built from CMS open data.
  arXiv  Detail & Related papers  (2026-08-26T15:32:44Z)
• Quantum Incremental Learning with Mixed State Prototypes [53.319426778720434]
  We introduce a novel quantum incremental learning framework based on trainable mixed-state prototypes.<n>Our model achieves high-dimensional feature concentration using a minimal number of qubits.
  arXiv  Detail & Related papers  (2026-08-11T04:22:42Z)
• LLM-Guided Initialization for Accelerated Hybrid Quantum-Classical Medical Image Classification [0.0]
  This paper evaluates AdaInit (Adaptive Initialization), proposed by Zhuang and Cunningham, which uses large language models to propose initial parameters for quantum neural networks.<n>AdaInit delivers 14.6 times higher gradient at random, producing 160 times faster convergence and maintaining the same classification accuracy of 61.4 percent.<n>The findings validate AdaInit in a medical imaging setting and demonstrate its compatibility with GPU-accelerated quantum backends for practical speedups.
  arXiv  Detail & Related papers  (2026-07-29T07:24:48Z)
• Entropy Estimation in Multi-Qutrit Systems via Variational and Classical Neural Networks [0.0]
  We present a systematic study of von Neumann entropy estimation in multi-qutrit quantum systems using variational quantum algorithms (VQAs) and classical convolutional neural networks (CNNs)<n>For systems up to three qutrits, we construct and evaluate 11 hardware-efficient SU(3)-inspired ansatzes.<n>For larger systems (two to five qutrits), we use a CNN trained on measurement outcomes from tensor-product mutually unbiased bases. The model achieves accurate and stable predictions and exhibits a systematic improvement in performance with system size.
  arXiv  Detail & Related papers  (2026-06-18T17:22:13Z)
• Layer-wise QUBO-Based Training of CNN Classifiers for Quantum Annealing [0.0]
  We propose an iterative framework based on Quadratic Un Binary Optimization (QUBO) for training the head of convolutional neural networks (CNNs)<n>A per-output decomposition splits the $C$-class problem into $C$ independent QUBOs, each with $(d+1)K$ binary variables, where $d$ is the feature dimension and $K$ is the bit precision.<n>We evaluate the method on six image-classification benchmarks (sklearn digits, MNIST, Fashion-MNIST, CIFAR-10, EMNIST, KMNIST)
  arXiv  Detail & Related papers  (2026-03-03T13:10:36Z)
• Parallel Multi-Circuit Quantum Feature Fusion in Hybrid Quantum-Classical Convolutional Neural Networks for Breast Tumor Classification [0.0]
  We present a hybrid Quantum-Classical Convolutional Neural Network (QCNN) architecture designed for the binary classification of the BreastMNIST dataset.<n>Our results indicate that hybrid QCNN architectures can leverage entanglement and quantum feature fusion to enhance medical image classification tasks.
  arXiv  Detail & Related papers  (2025-11-29T17:47:14Z)
• Practical insights on the effect of different encodings, ansätze and measurements in quantum and hybrid convolutional neural networks [37.69303106863453]
  This study investigates the design choices of parameterized quantum circuits (PQCs) within quantum and hybrid convolutional neural network (HQNN and QCNN) architectures.<n>We evaluate the performance implications of data encoding techniques, variational ans"atze, and measurement in approx. 500 distinct model configurations.
  arXiv  Detail & Related papers  (2025-06-25T12:10:11Z)
• Deep Feature Response Discriminative Calibration [37.81540706307031]
  optimization techniques, such as ResNet and SENet, have been proposed to improve model accuracy. They lack the discriminative calibration for different features, thereby introducing limitations in the model output. We propose a method that discriminatively calibrates feature responses.
  arXiv  Detail & Related papers  (2024-11-16T10:48:32Z)
• Towards a tailored mixed-precision sub-8-bit quantization scheme for Gated Recurrent Units using Genetic Algorithms [39.979007027634196]
  Gated Recurrent Units (GRU) are difficult to tune due to their dependence on an internal state. We propose a modular integer quantization scheme for GRUs where the bit width of each operator can be selected independently.
  arXiv  Detail & Related papers  (2024-02-19T16:24:20Z)
• Non-parametric Greedy Optimization of Parametric Quantum Circuits [2.77390041716769]
  This work aims to reduce depth and gate count of PQCs by replacing parametric gates with their approximate fixed non-parametric representations. We observe roughly 14% reduction in depth and 48% reduction in gate count at the cost of 3.33% reduction in inferencing accuracy.
  arXiv  Detail & Related papers  (2024-01-27T15:29:38Z)
• Iterative Qubit Coupled Cluster using only Clifford circuits [36.136619420474766]
  An ideal state preparation protocol can be characterized by being easily generated classically. We propose a method that meets these requirements by introducing a variant of the iterative qubit coupled cluster (iQCC) We demonstrate the algorithm's correctness in ground-state simulations and extend our study to complex systems like the titanium-based compound Ti(C5H5)(CH3)3 with a (20, 20) active space.
  arXiv  Detail & Related papers  (2022-11-18T20:31:10Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• A quantum algorithm for training wide and deep classical neural networks [72.2614468437919]
  We show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We numerically demonstrate that the MNIST image dataset satisfies such conditions. We provide empirical evidence for $O(log n)$ training of a convolutional neural network with pooling.
  arXiv  Detail & Related papers  (2021-07-19T23:41:03Z)

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.