Reservoir computing (RC) is a computational framework for information processing based on neural network. It can be implemented with different physical platforms, principally, electronic architectures and photonic architectures. Photonic RC shows potential path to ultra-fast and efficient processing beyond the traditional Turing-von Neumann computer architecture. Typical photonics RC consider specifically a semiconductor laser (SL) with delayed feedback as reservoir substrate. Basically, the SL is a kind of type B laser, needing enough long delay feedback for the high dimensional chaos generation and for the RC mapping. But on the other hand, long delay feedback leads to the setup big size, being nonconductive of integration implement and stable operation performance in real world. To solve the problem of a huge size, we propose a new photonics RC scheme that using chaotic SL hybrid with Si3N4 micro-resonator, which works as the storage layer and feedback loop. The Si3N4 micro-resonator could help SL producing high-dimensional chaos and reaching high-complexity RC. Meanwhile, the size of Si3N4 micro-resonator is highly compressed at the level of ten micrometers, thereby realizing a size compression of over ten times than that of typical photonics RC setup. In our experiment, we make the free spectrum range (FSR) of micro-resonator is 35GHz, reaching the nonlinear frequency of SL. Then, with careful operation, two-mode mixing chaos can be realized, being very conductive for the photonics RC applications. These results are conducive for the development of on-chip photonic RC.
Convolutional neural network (CNN) has attracted widespread attention in image feature extraction and speech recognition owing to greatly reducing the complexity of model parameters and the number of weights, but it cannot be separated from the support of hardware accelerator. The limitations of electronic devices in terms of power, speed, and size make it difficult for current electron accelerators to meet the computational power requirements of future large-scale convolution operations. Here, we proposed a photonic vector architecture. This structure combines time, space and wavelength, and the non-volatile phase change material and the integrated microcomb form an optical matrix multiplier to realize memory calculation, thus reducing the energy consumption of reading weight data. The tooth spacing of the integrated microcomb is more than 100 GHz, and the microcomb coverage is from 1510 nm to 1610 nm. Finally, we replace the weight values in the CNN with the optimal weight values that the optics can achieve. The final recognition accuracy reached 97.04%, which is comparable to the efficiency of the first electronic equipment. Our results could be helpful for the development of non-volatile and ultra-fast optical neural network (ONN) with feathers of low energy consumption and high integration.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.