Related papers: Magneto-Ionic Physical Reservoir Computing
A hitherto unexploited characteristic feature of emerging iontronic devices for information processing is the intrinsic mobility of the medium (water) of dissolved ions in aqueous electrolytes, which therefore not only respond to voltage…
Magneto-ionics, by which the magnetic properties of a thin layer can be modified through the migration of ions within a liquid or solid electrolyte, is a fast developing research field. This is mainly due to the perspective of energy…
This chapter provides a comprehensive survey of the researches and motivations for hardware implementation of reservoir computing (RC) on neuromorphic electronic systems. Due to its computational efficiency and the fact that training…
Inspired by the human brain, there is a strong effort to find alternative models of information processing capable of imitating the high energy efficiency of neuromorphic information processing. One possible realization of cognitive…
This paper extends the notion of information processing capacity for non-independent input signals in the context of reservoir computing (RC). The presence of input autocorrelation makes worthwhile the treatment of forecasting and filtering…
Memristors are non-volatile nano-resistors. Their resistance can be tuned by applied currents or voltages and set to a large number of levels between two limit values. Thanks to these properties, memristors are ideal building blocks for a…
A numerical analysis on the computational capability of physical reservoir computing utilizing a spin-torque oscillator with two free layers is reported. Conventional spintronics devices usually consist of two ferromagnets, where the…
Classification of multivariate time series (MTS) has been tackled with a large variety of methodologies and applied to a wide range of scenarios. Reservoir Computing (RC) provides efficient tools to generate a vectorial, fixed-size…
Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained. In the large size limit, such random neural networks have a deep…
The current efforts to fabricate non-volatile magnetic recording media with a high areal density is deteriorated by the increasing temporal instability of the stored information. If the stored energy per magnetic particle competes with the…
Physical reservoir computing exploits the nonlinear dynamics of a physical system to perform information processing tasks. Josephson junctions (JJs), as nonlinear superconducting devices with rich dynamical behavior, represent promising yet…
Recurrent Neural Networks (RNN) are extensively employed for processing sequential data such as time series. Reservoir computing (RC) has drawn attention as an RNN framework due to its fixed network that does not require training, making it…
Binary stochastic neurons (BSN's) form an integral part of many machine learning algorithms, motivating the development of hardware accelerators for this complex function. It has been recognized that hardware BSN's can be implemented using…
Spintronics-based nonvolatile components in neuromorphic circuits offer the possibility of realizing novel functionalities at low power. Current-controlled electrical switching of magnetization is actively researched in this context.…
Physical Reservoir Computing (PRC) is a recently developed variant of Neuromorphic Computing, where a pertinent physical system effectively projects information encoded in the input signal into a higher-dimensional space. While various…
Spatiotemporal information processing is fundamental to brain functions. The present study investigates a canonic neural network model for spatiotemporal pattern recognition. Specifically, the model consists of two modules, a reservoir…
So far, magneto-ionics, understood as voltage-driven ion transport in magnetic materials, has largely relied on controlled migration of oxygen ion/vacancy and, to a lesser extent, lithium and hydrogen. Here, we demonstrate efficient,…
In-memory computing is a promising approach to addressing the processor-memory data transfer bottleneck in computing systems. We propose Spin-Transfer Torque Compute-in-Memory (STT-CiM), a design for in-memory computing with Spin-Transfer…
Reservoir computing is a machine learning algorithm that excels at predicting the evolution of time series, in particular, dynamical systems. Moreover, it has also shown superb performance at solving partial differential equations. In this…
This paper addresses the reservoir design problem in the context of delay-based reservoir computers for multidimensional input signals, parallel architectures, and real-time multitasking. First, an approximating reservoir model is presented…