Quantum Machine Learning Advances

The field of quantum machine learning is rapidly advancing, with a focus on developing innovative methods that leverage the power of quantum computing to improve classical machine learning models. Recent research has explored the application of quantum-inspired techniques, such as quantum augmentations and quantum-inspired encoding strategies, to enhance the performance of classical machine learning models. Additionally, there has been a growing interest in using quantum machine learning models, such as Quantum Neural Networks (QNNs) and Quantum Support Vector Machines (QSVMs), to tackle complex tasks, including time-series forecasting, classification, and clustering. These models have shown promising results, outperforming classical models in some cases.

Noteworthy papers include:

  • Quantum Approximate Optimization Algorithm for Spatiotemporal Forecasting of HIV Clusters, which achieved 92% accuracy in cluster detection and 94% accuracy in HIV prevalence forecasting.
  • AI-Hybrid TRNG, a deep-learning framework that extracts near-uniform entropy from physical noise, eliminating the need for bulky quantum devices or expensive laboratory-grade RF receivers.
  • Quantum Machine Learning in Transportation, which used QSVM and QNN to model complex skin conductance response events that reflect pedestrian stress in a virtual reality road crossing experiment.

Sources

Boosting Classification with Quantum-Inspired Augmentations

Quantum Neural Networks for Wind Energy Forecasting: A Comparative Study of Performance and Scalability with Classical Models

Quantum Inspired Encoding Strategies for Machine Learning Models: Proposing and Evaluating Instance Level, Global Discrete, and Class Conditional Representations

Graph Neural Networks in Wind Power Forecasting

AI-Hybrid TRNG: Kernel-Based Deep Learning for Near-Uniform Entropy Harvesting from Physical Noise

Quantum Approximate Optimization Algorithm for Spatiotemporal Forecasting of HIV Clusters

MichelangeRoll: Sculpting Rational Distributions Exactly and Efficiently

Quantum Machine Learning in Transportation: A Case Study of Pedestrian Stress Modelling

Surrogate Modeling via Factorization Machine and Ising Model with Enhanced Higher-Order Interaction Learning

EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer

Built with on top of