Simulation platform for pattern recognition based on reservoir computing with memristor networks
arXiv:2112.00248 · doi:10.1038/s41598-022-13687-z
Abstract
Memristive systems and devices are potentially available for implementing reservoir computing (RC) systems applied to pattern recognition. However, the computational ability of memristive RC systems depends on intertwined factors such as system architectures and physical properties of memristive elements, which complicates identifying the key factor for system performance. Here we develop a simulation platform for RC with memristor device networks, which enables testing different system designs for performance improvement. Numerical simulations show that the memristor-network-based RC systems can yield high computational performance comparable to that of state-of-the-art methods in three time series classification tasks. We demonstrate that the excellent and robust computation under device-to-device variability can be achieved by appropriately setting network structures, nonlinearity of memristors, and pre/post-processing, which increases the potential for reliable computation with unreliable component devices. Our results contribute to an establishment of a design guide for memristive reservoirs toward a realization of energy-efficient machine learning hardware.
arXiv comment14 pages, 7 figures, 5 supplementary figures
References in corpus (7)
- Recent Advances in Physical Reservoir Computing: A Review
- The elusive memristor: properties of basic electrical circuits
- Optoelectronic Reservoir Computing
- Spin waves propagating through a stripe magnetic domain structure and their applications to reservoir computing
- Analysis of Dynamic Linear and Non-linear Memristor Device Models for Emerging Neuromorphic Computing Hardware Design
- Role of non-linear data processing on speech recognition task in the framework of reservoir computing
- Spoken Digit Classification by In-Materio Reservoir Computing with Neuromorphic Atomic Switch Networks