7 papers
Boltzmann Attention: Learnable Ising Couplings for Cooperative Attention
Gilhan Kim, Daniel K. Park
Attention mechanisms are central to modern sequence models, yet standard attention computes relevance primarily through individual query--key similarities. Although softmax normali…
Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
Gilhan Kim, Daniel K. Park
Energy-based models provide a natural bridge between statistical physics and machine learning by representing data through structured energy landscapes. Boltzmann machines are a pa…
Neural quantum support vector data description for one-class classification
Changjae Im, Hyeondo Oh, Daniel K. Park
One-class classification (OCC) is a fundamental problem in machine learning with numerous applications, such as anomaly detection and quality control. With the increasing complexit…
Noise-adaptive hybrid quantum convolutional neural networks based on depth-stratified feature extraction
Taehyun Kim, Israel F. Araujo, Daniel K. Park
Hierarchical quantum classifiers, such as quantum convolutional neural networks (QCNNs), represent recent progress toward designing effective and feasible architectures for quantum…
Improving Generalization and Trainability of Quantum Eigensolvers via Graph Neural Encoding
Jungyun Lee, Daniel K. Park
Determining the ground state of a many-body Hamiltonian is a central problem across physics, chemistry, and combinatorial optimization, yet it is often classically intractable due…
Improving Quantum Machine Learning via Heat-Bath Algorithmic Cooling
Nayeli A. RodrÃguez-Briones, Daniel K. Park
This work introduces an approach rooted in quantum thermodynamics to enhance sampling efficiency in quantum machine learning (QML). We propose conceptualizing quantum supervised le…