• Publications
  • Influence
Recent Advances in Physical Reservoir Computing: A Review
TLDR
Physical reservoir computing is a computational framework suited for temporal/sequential data processing. Expand
  • 208
  • 2
  • PDF
Wave-Based Reservoir Computing by Synchronization of Coupled Oscillators
TLDR
We propose wave-based computing based on coupled oscillators to avoid the inter-connection bottleneck in large scale and densely integrated cognitive systems and reduce the training cost of large and dense cognitive systems. Expand
  • 17
Photonic Reservoir Computing Based on Laser Dynamics with External Feedback
TLDR
We propose a concept of reservoir computing consisting of a semiconductor laser subject to external feedback by a mirror, where input signal is supplied as modulation pattern of mirror reflectivity. Expand
  • 12
Exploiting Heterogeneous Units for Reservoir Computing with Simple Architecture
TLDR
We show that heterogeneity in reservoir units can be beneficial in reducing the prediction error in the reservoir computing system with a simple cycle reservoir. Expand
  • 11
  • PDF
Dynamics of Reservoir Computing at the Edge of Stability
TLDR
We investigate reservoir computing systems whose dynamics are at critical bifurcation points based on center manifold theorem and show that the center manifold defines mapping of the input dynamics to higher dimensional space. Expand
  • 10
Waveform Classification by Memristive Reservoir Computing
TLDR
We study the memristive reservoir computing where a network of memristors, instead of recurrent neural networks, provides a nonlinear mapping from input sequential signals to high-dimensional spatiotemporal dynamics. Expand
  • 12
Complex-Valued Neural Networks for Wave-Based Realization of Reservoir Computing
TLDR
In this paper, we discuss the significance of complex-valued neural-network (CVNN) framework in energy-efficient neural networks, in particular in wave-based reservoir networks. Expand
  • 7
Spatially Arranged Sparse Recurrent Neural Networks for Energy Efficient Associative Memory
TLDR
The development of hardware neural networks, including neuromorphic hardware, has been accelerated over the past few years. Expand
  • 10
Computational Performance of Echo State Networks with Dynamic Synapses
TLDR
The echo state network is a framework for temporal data processing, such as recognition, identification, classification and prediction. Expand
  • 3
Simulation Study of Physical Reservoir Computing by Nonlinear Deterministic Time Series Analysis
TLDR
We investigate dynamics of physical reservoir computing by numerical simulations. Expand
  • 5