Expand description
Quantum Machine Learning Layers Framework
This module provides a comprehensive implementation of quantum machine learning layers, including parameterized quantum circuits, quantum convolutional layers, quantum recurrent networks, and hybrid classical-quantum training algorithms. This framework enables quantum advantage in machine learning applications with hardware-aware optimization.
Structs§
- Adversarial
Training Config - Adversarial training configuration
- Attention
Head - Attention head structure
- Benchmarking
Protocols - Benchmarking protocols
- Caching
Config - Caching configuration
- Classical
Preprocessing Config - Classical preprocessing configuration
- Computation
Optimization Config - Computation optimization configuration
- Convolutional
Filter - Convolutional filter structure
- Dense
Connection - Dense layer connection
- Early
Stopping Config - Early stopping configuration
- Ensemble
Methods Config - Ensemble methods configuration
- Error
Mitigation Config - Error mitigation configuration
- Feature
Selection Config - Feature selection configuration
- Gradient
Flow Config - Gradient flow configuration for hybrid training
- Hardware
Optimization Config - Hardware optimization configuration
- Hybrid
Training Config - Hybrid training configuration
- LSTM
Gate - LSTM gate structure
- Memory
Optimization Config - Memory optimization configuration
- Noise
Aware Training Config - Noise-aware training configuration
- Noise
Characterization Config - Noise characterization configuration
- Noise
Injection Config - Noise injection configuration
- Noise
Parameters - Noise parameters for quantum devices
- PQCGate
- Parameterized quantum circuit gate
- Parallelization
Config - Parallelization configuration
- Parameterized
Quantum Circuit Layer - Parameterized Quantum Circuit Layer
- Performance
Optimization Config - Performance optimization configuration
- QMLBenchmark
Results - QML benchmark results
- QMLConfig
- Quantum machine learning configuration
- QMLEpoch
Metrics - Training metrics for a single epoch
- QMLLayer
Config - QML layer configuration
- QMLStats
- QML framework statistics
- QMLTraining
Config - QML training configuration
- QMLTraining
Result - Training result for QML framework
- QMLTraining
State - Training state for QML framework
- QMLUtils
- Utility functions for QML
- Quantum
Advantage Metrics - Quantum advantage metrics
- Quantum
Attention Layer - Quantum Attention Layer
- Quantum
Convolutional Layer - Quantum Convolutional Layer
- Quantum
Dense Layer - Quantum Dense Layer (fully connected)
- QuantumLSTM
Layer - Quantum LSTM Layer
- QuantumML
Framework - Main quantum machine learning layers framework
- Regularization
Config - Regularization configuration
- Robust
Training Config - Robust training configuration
- Virtual
Distillation Config - Virtual distillation configuration
Enums§
- Adversarial
Attack Method - Adversarial attack methods
- Adversarial
Defense Method - Adversarial defense methods
- Alternating
Schedule - Alternating training schedules for hybrid systems
- Ansatz
Type - Ansatz types for parameterized quantum circuits
- Calibration
Frequency - Calibration frequency
- Classical
Architecture - Classical neural network architectures for hybrid training
- Connectivity
Constraints - Connectivity constraints
- Data
Encoding Method - Data encoding methods for quantum circuits
- Distillation
Protocol - Distillation protocols
- Ensemble
Method - Ensemble methods
- Entanglement
Pattern - Entanglement patterns
- Feature
Selection Method - Feature selection methods
- Gradient
Method - Gradient computation methods
- Hardware
Optimization Level - Hardware optimization levels
- LSTM
Gate Type - LSTM gate types
- Learning
Rate Schedule - Learning rate schedules
- Noise
Characterization Method - Noise characterization methods
- Noise
Type - Noise types for training
- Optimizer
Type - Optimizer types
- PQCGate
Type - Types of PQC gates
- QMLArchitecture
Type - QML architecture types
- QMLLayer
Type - Types of QML layers
- QMLTraining
Algorithm - QML training algorithms
- Quantum
Classical Interface - Quantum-classical interfaces
- Quantum
Hardware Target - Quantum hardware targets
- Rotation
Gate - Rotation gates for parameterized circuits
- Scaling
Method - Scaling methods for classical preprocessing
- TwoQubit
Gate - Two-qubit gates
- Voting
Strategy - Voting strategies for ensembles
Traits§
- QMLLayer
- Trait for QML layers
Functions§
- benchmark_
quantum_ ml_ layers - Benchmark quantum machine learning implementations