Input-dependence in quantum reservoir computing
arXiv:2412.08322 · doi:10.1103/3775-4hfd
Abstract
Quantum reservoir computing is an emergent field in which quantum dynamical systems are exploited for temporal information processing. In previous work, it was found a feature that makes a quantum reservoir valuable: contractive dynamics of the quantum reservoir channel toward input-dependent fixed points. These results are enhanced in this paper by finding conditions that guarantee a crucial aspect of the reservoir's design: distinguishing between different input sequences to ensure a faithful representation of temporal input data. This is implemented by finding a condition that guarantees injectivity in reservoir computing filters, with a special emphasis on the quantum case. We provide several examples and focus on a family of quantum reservoirs that is much used in the literature; it consists of an input-encoding quantum channel followed by a strictly contractive channel that enforces the echo state and the fading memory properties. This work contributes to analyzing valuable quantum reservoirs in terms of their input dependence.
16 pages, 2 figures
References in corpus (30)
- Open Quantum Systems. An Introduction
- Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
- The Bloch Vector for N-Level Systems
- Attractor Reconstruction by Machine Learning
- Harnessing disordered quantum dynamics for machine learning
- Characterization of the Positivity of the Density Matrix in Terms of the Coherence Vector Representation
- Any Quantum Network is Structurally Controllable by a Single Driving Signal
- Dynamical phase transitions in quantum reservoir computing
- Temporal Information Processing on Noisy Quantum Computers
- Time Series Quantum Reservoir Computing with Weak and Projective Measurements
- Gaussian states of continuous-variable quantum systems provide universal and versatile reservoir computing
- Ergodic and Mixing Quantum Channels in Finite Dimensions
- Hybrid quantum-classical reservoir computing of thermal convection flow
- Chaos on compact manifolds: Differentiable synchronizations beyond the Takens theorem
- Dissipation as a resource for Quantum Reservoir Computing
- The Reservoir Learning Power across Quantum Many-Boby Localization Transition
- Feedback-driven quantum reservoir computing for time-series analysis
- Learning strange attractors with reservoir systems
- Quantum reservoir computing in finite dimensions
- Learn to Synchronize, Synchronize to Learn
- Memory and forecasting capacities of nonlinear recurrent networks
- Overcoming the Coherence Time Barrier in Quantum Machine Learning on Temporal Data
- Role of coherence in many-body Quantum Reservoir Computing
- Extending echo state property for quantum reservoir computing
- Optimization of the Memory Reset Rate of a Quantum Echo-State Network for Time Sequential Tasks
- Retrieving past quantum features with deep hybrid classical-quantum reservoir computing
- Squeezing as a resource for time series processing in quantum reservoir computing
- Quantum Next Generation Reservoir Computing: An Efficient Quantum Algorithm for Forecasting Quantum Dynamics
- Liouvillian skin effect in quantum neural networks
- Effects of dissipation in reservoir computing using a spin qubit array