Reservoir computing with a single time-delay autonomous Boolean node

Abstract

We demonstrate reservoir computing with a physical system using a single autonomous Boolean logic element with time-delay feedback. The system generates a chaotic transient with a window of consistency lasting between 30 and 300 ns, which we show is sufficient for reservoir computing. We then characterize the dependence of computational performance on system parameters to find the best operating point of the reservoir. When the best parameters are chosen, the reservoir is able to classify short input patterns with performance that decreases over time. In particular, we show that four distinct input patterns can be classified for 70 ns, even though the inputs are only provided to the reservoir for 7.5 ns.

5 pages, 5 figures

References in corpus (3)

• Transient scaling and resurgence of chimera states in networks of Boolean phase oscillators
• Computational Capabilities of Random Automata Networks for Reservoir Computing
• Synchronization of Coupled Boolean Phase Oscillators

Cited by in corpus (29)

• Recent Advances in Physical Reservoir Computing: A Review
• Attractor Reconstruction by Machine Learning
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Quantum reservoir computing with a single nonlinear oscillator
• A Substrate-Independent Framework to Characterise Reservoir Computers
• Anticipating synchronization with machine learning
• Rapid Time Series Prediction with a Hardware-Based Reservoir Computer
• Large-scale spatiotemporal photonic reservoir computer for image classification
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops
• Delayed Dynamical Systems: Networks, Chimeras and Reservoir Computing
• Embodiment of Learning in Electro-Optical Signal Processors
• Adaptable Hamiltonian neural networks
• Using reservoir computer to predict and prevent extreme events
• Reservoir Computing Approach to Quantum State Measurement
• Robust Forecasting using Predictive Generalized Synchronization in Reservoir Computing
• Finding nonlinear system equations and complex network structures from data: a sparse optimization approach
• In-materio neuromimetic devices: Dynamics, information processing and pattern recognition
• Machine Learning Potential of a Single Pendulum
• Structured light entities, chaos and nonlocal maps
• Reservoir Computing with Superconducting Electronics
• Forecasting Using Reservoir Computing: The Role of Generalized Synchronization
• Model-free prediction of spatiotemporal dynamical systems with recurrent neural networks: Role of network spectral radius
• A high-performance analog Max-SAT solver and its application to Ramsey numbers
• Next-Generation Reservoir Computing for Dynamical Inference
• Long-term prediction of chaotic systems with recurrent neural networks
• Physical reservoir computing using finitely-sampled quantum systems
• Infinite-dimensional Folded-in-time Deep Neural Networks