The Computational Capacity of LRC, Memristive and Hybrid Reservoirs
- URL: http://arxiv.org/abs/2009.00112v3
- Date: Mon, 26 Sep 2022 17:01:01 GMT
- Title: The Computational Capacity of LRC, Memristive and Hybrid Reservoirs
- Authors: Forrest C. Sheldon, Artemy Kolchinsky, Francesco Caravelli
- Abstract summary: Reservoir computing is a machine learning paradigm that uses a high-dimensional dynamical system, or emphreservoir, to approximate and predict time series data.
We analyze the feasibility and optimal design of electronic reservoirs that include both linear elements (resistors, inductors, and capacitors) and nonlinear memory elements called memristors.
Our electronic reservoirs can match or exceed the performance of conventional "echo state network" reservoirs in a form that may be directly implemented in hardware.
- Score: 1.657441317977376
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Reservoir computing is a machine learning paradigm that uses a
high-dimensional dynamical system, or \emph{reservoir}, to approximate and
predict time series data. The scale, speed and power usage of reservoir
computers could be enhanced by constructing reservoirs out of electronic
circuits, and several experimental studies have demonstrated promise in this
direction. However, designing quality reservoirs requires a precise
understanding of how such circuits process and store information. We analyze
the feasibility and optimal design of electronic reservoirs that include both
linear elements (resistors, inductors, and capacitors) and nonlinear memory
elements called memristors. We provide analytic results regarding the
feasibility of these reservoirs, and give a systematic characterization of
their computational properties by examining the types of input-output
relationships that they can approximate. This allows us to design reservoirs
with optimal properties. By introducing measures of the total linear and
nonlinear computational capacities of the reservoir, we are able to design
electronic circuits whose total computational capacity scales extensively with
the system size. Our electronic reservoirs can match or exceed the performance
of conventional "echo state network" reservoirs in a form that may be directly
implemented in hardware.
Related papers
- A theoretical framework for reservoir computing on networks of organic electrochemical transistors [0.0]
Organic electrochemical transistors (OECTs) are physical devices with nonlinear transient properties.
We present a theoretical framework for simulating reservoir computers using OECTs as the non-linear units.
We show that such an implementation can accurately predict the Lorenz attractor with comparable performance to standard reservoir computer implementations.
arXiv Detail & Related papers (2024-08-17T15:04:09Z) - Deep Photonic Reservoir Computer for Speech Recognition [49.1574468325115]
Speech recognition is a critical task in the field of artificial intelligence and has witnessed remarkable advancements.
Deep reservoir computing is energy efficient but exhibits limitations in performance when compared to more resource-intensive machine learning algorithms.
We propose a photonic-based deep reservoir computer and evaluate its effectiveness on different speech recognition tasks.
arXiv Detail & Related papers (2023-12-11T17:43:58Z) - Randomized Polar Codes for Anytime Distributed Machine Learning [66.46612460837147]
We present a novel distributed computing framework that is robust to slow compute nodes, and is capable of both approximate and exact computation of linear operations.
We propose a sequential decoding algorithm designed to handle real valued data while maintaining low computational complexity for recovery.
We demonstrate the potential applications of this framework in various contexts, such as large-scale matrix multiplication and black-box optimization.
arXiv Detail & Related papers (2023-09-01T18:02:04Z) - Optimization of a Hydrodynamic Computational Reservoir through Evolution [58.720142291102135]
We interface with a model of a hydrodynamic system, under development by a startup, as a computational reservoir.
We optimized the readout times and how inputs are mapped to the wave amplitude or frequency using an evolutionary search algorithm.
Applying evolutionary methods to this reservoir system substantially improved separability on an XNOR task, in comparison to implementations with hand-selected parameters.
arXiv Detail & Related papers (2023-04-20T19:15:02Z) - Reservoir Computing Using Complex Systems [0.0]
Reservoir Computing is a machine learning framework for utilising physical systems for computation.
We show how a single node reservoir can be employed for computation and explore the available options to improve the computational capability of the physical reservoirs.
arXiv Detail & Related papers (2022-12-17T00:25:56Z) - Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling
and Design [68.1682448368636]
We present a supervised pretraining approach to learn circuit representations that can be adapted to new unseen topologies or unseen prediction tasks.
To cope with the variable topological structure of different circuits we describe each circuit as a graph and use graph neural networks (GNNs) to learn node embeddings.
We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties.
arXiv Detail & Related papers (2022-03-29T21:18:47Z) - Simulation platform for pattern recognition based on reservoir computing
with memristor networks [1.5664378826358722]
We develop a simulation platform for reservoir computing (RC) with memristor device networks.
We 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.
arXiv Detail & Related papers (2021-12-01T03:06:13Z) - Automatic digital twin data model generation of building energy systems
from piping and instrumentation diagrams [58.720142291102135]
We present an approach to recognize symbols and connections of P&ID from buildings in a completely automated way.
We apply algorithms for symbol recognition, line recognition and derivation of connections to the data sets.
The approach can be used in further processes like control generation, (distributed) model predictive control or fault detection.
arXiv Detail & Related papers (2021-08-31T15:09:39Z) - Task Agnostic Metrics for Reservoir Computing [0.0]
Physical reservoir computing is a computational paradigm that enables temporal pattern recognition in physical matter.
The chosen dynamical system must have three desirable properties: non-linearity, complexity, and fading memory.
We show that, in general, systems with lower damping reach higher values in all three performance metrics.
arXiv Detail & Related papers (2021-08-03T13:58:11Z) - Insight into Delay Based Reservoir Computing via Eigenvalue Analysis [0.0]
We show that any dynamical system used as a reservoir can be analyzed in this way.
Optimal performance is found for a system with the eigenvalues having real parts close to zero and off-resonant imaginary parts.
arXiv Detail & Related papers (2020-09-16T20:41:47Z) - Efficient simulatability of continuous-variable circuits with large
Wigner negativity [62.997667081978825]
Wigner negativity is known to be a necessary resource for computational advantage in several quantum-computing architectures.
We identify vast families of circuits that display large, possibly unbounded, Wigner negativity, and yet are classically efficiently simulatable.
We derive our results by establishing a link between the simulatability of high-dimensional discrete-variable quantum circuits and bosonic codes.
arXiv Detail & Related papers (2020-05-25T11:03:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.