Combination of Organic‐Based Reservoir Computing and Spiking Neuromorphic Systems for a Robust and Efficient Pattern Classification

Abstract

Nowadays, neuromorphic systems based on memristors are considered promising approaches to the hardware realization of artificial intelligence systems with efficient information processing. However, a major bottleneck in the physical implementation of these systems is the strong dependence of their performance on the unavoidable variations (cycle‐to‐cycle, c2c, or device‐to‐device, d2d) of memristive devices. Recently, reservoir computing (RC) and spiking neuromorphic systems (SNSs) are separately proposed as valuable options to partially mitigate this problem. Herein, both approaches are combined to create a fully organic system based on 1) volatile polyaniline memristive devices for the reservoir layer and 2) nonvolatile parylene memristors for the SNS readout layer. This combination provides a simpler SNS training procedure compared with the formal neural networks and results in greater robustness to device variability, while ensuring the extraction and encoding of the input critical features (performed by the polyaniline reservoir) and the analysis and classification performed by the SNS layer. Furthermore, the spatiotemporal pattern recognition of the system brings us closer to the implementation of efficient and reliable brain‐inspired computing systems built with partially unreliable analog elements.

Adapted MLP-Mixer network based on crossbar arrays of fast and multilevel switching (Co–Fe–B)x(LiNbO3)100−x nanocomposite memristors

“…33 Another way to mitigate the problem of memristive variations is to realize spiking NCSs with bio-inspired algorithms. [34][35][36][37][38] Although there is certain progress in the training of spiking NCSs, such as deep learning-inspired approaches, 39 surrogate gradient learning 40 and Python packages for spiking NCSs modelling like SpikingJelly 41 and SNNTorch, 39 efficient training algorithms for spiking NCSs are still underdeveloped, which complicates the transfer of memristor-based spiking NCSs from the current device level to a large system level. 42 Consequently, the search for new efficient memristor-based NCS architectures and training algorithms is of high interest.…”

Unveiling transient current response in bilayer oxide-based physical reservoirs for time-series data analysis

“…27 Apart from the backpropagation processing, the spiking neuromorphic system was also established in the work of Matsukatova et al to perform computation based on the spike-timing-dependent plasticity learning rule with low-power spiking signals. 28 In this study, we demonstrate a physical reservoir based on the bilayer oxide-based dynamic memristor, which utilizes an oxide interface instead of the conductive filament-based mechanism and functions as a nonlinear dynamical system with short-term memory (STM). The platinum (Pt) is selected as the bottom electrode for its high work function to form Schottky barrier with most of the oxide semiconductors and dielectrics.…”

“…27 Apart from the backpropagation processing, the spiking neuromorphic system was also established in the work of Matsukatova et al to perform computation based on the spike-timing-dependent plasticity learning rule with low-power spiking signals. 28…”

Harness Background Lighting for Separability Enhancement in Optical Sensing Reservoir for Temporal Signal Processing Utilizing Amorphous IGZO Neuromorphic Transistors

“…As a result, reservoir computing (RC) has emerged as a promising algorithm for processing temporal data. − In the RC, temporal signals are transformed into high-dimensional states, enabling complex inputs to become linearly separable on the basis of reservoir states. This transformation of inputs enables efficient processing through a simple readout layer, resulting in significant reductions in network scale and training cost. , Recently, several physical reservoirs have been proposed, including those utilizing metal oxides, ,, two-dimensional materials, − and organics. − The effectiveness of the RC system, which is characterized by fading memory and distinct reservoir states, has been successfully demonstrated in these studies. Nonetheless, only a few of these reservoirs possess the combined features of light responsiveness, CMOS compatibility, and scalability.…”