Quantum Active Learning: Choosing What to Label
Quantum active learning chooses which data points to label next to train a quantum model efficiently. Methods, benefits and challenges.
BasicsAlgorithmsHardwareError CorrectionCryptographyMachine LearningInformation TheoryPhysics & SimulationApplicationsIndustry & Careers
Tagged: Artificial Intelligence
110 articles
Quantum Adversarial Learning and Robustness
Adversarial attacks can fool quantum classifiers just as they fool classical ones. Types of attacks, defenses and robustness evaluation.
Quantum Meta-Learning: Learning to Learn on Qubits
Quantum meta-learning uses classical or quantum models to learn good starting parameters for quantum circuits. Ideas, algorithms and challenges.
Quantum Transfer Learning Between Circuits
Quantum transfer learning reuses a trained classical or quantum model for a new task on quantum hardware. How it works and its challenges.
Quantum Stochastic Gradient Descent (QSGD)
Stochastic gradient descent in quantum machine learning: how gradients of quantum circuits are estimated from samples and the challenges involved.
Quantum Graph Neural Networks and Their Circuits
Quantum graph neural networks encode graph structure into quantum circuits. Architecture, training, benchmarks and prospects.
Quantum Latent Space Models and Representation
Latent space models learn compact representations of data. How quantum versions would work, possible uses and comparison with classical models.
Quantum Feature Spaces: Where the Advantage Hides
Quantum feature spaces are where quantum machine learning is supposed to find its advantage. Encodings, feature maps and current limitations.
Quantum Annealing for Machine Learning Tasks
How quantum annealers are used for machine learning tasks such as training and feature selection, and how they compare with classical methods.
Quantum Decision Trees and Query Complexity
Quantum decision trees and query complexity: how quantum algorithms evaluate decision trees and how they compare with classical ones.
Quantum Recurrent Neural Networks (QRNN)
Proposals for quantum recurrent neural networks, how they would handle sequences and time series, and the hardware limits today.
Quantum Convolutional Neural Networks (QCNN)
Quantum convolutional neural networks apply convolution and pooling layers to qubits. Their design, uses in classifying quantum states and challenges.
