Search

ABSTRACT: With the advent of the “Big Data Era”, improving data storage density and computation speed has become more and more urgent due to the rapid growth in different types of data. Flash memory with a floating gate (FG) structure is attracting great attention owing to its advantages of miniaturization, low power consumption and reliable data storage, which is very effective in solving the problems of large data capacity and high integration density. Meanwhile, the FG memory with charge storage principle can simulate synaptic plasticity perfectly, breaking the traditional von Neumann computing architecture and can be used as an artificial synapse for neuromorphic computations inspired by the human brain. Among many candidate materials for manufacturing devices, van der Waals (vdW) materials have attracted widespread attention due to their atomic thickness, high mobility, and sustainable miniaturization properties. Owing to the arbitrary stacking ability, vdW heterostructure combines rich physics and potential 3D integration, opening up various possibilities for new functional integrated devices with low power consumption and flexible applications. This paper provides a comprehensive review of memory devices based on vdW materials with FG structure, including the working principles and typical structures of FG structure devices, with a focus on the introduction of various high-performance FG memories and their versatile applications in neuromorphic computing. Finally, the challenges of neuromorphic devices based on FG structures are also discussed. This review will shed light on the design and fabrication of vdW material-based memory devices with FG engineering, helping to promote the development of practical and promising neuromorphic computing.

Recurrent neural networks (RNNs) have proven to be indispensable for processing sequential and temporal data, with extensive applications in language modeling, text generation, machine translation, and time-series forecasting. Despite their versatility, RNNs are frequently beset by significant training expenses and slow convergence times, which impinge upon their deployment in edge AI applications. Reservoir computing (RC), a specialized RNN variant, is attracting increased attention as a cost-effective alternative for processing temporal and sequential data at the edge. RC’s distinctive advantage stems from its compatibility with emerging memristive hardware, which leverages the energy efficiency and reduced footprint of analog in-memory and in-sensor computing, offering a streamlined and energy-efficient solution. This review offers a comprehensive explanation of RC’s underlying principles, fabrication processes, and surveys recent progress in nano-memristive device based RC systems from the viewpoints of in-memory and in-sensor RC function. It covers a spectrum of memristive device, from established oxide-based memristive device to cutting-edge material science developments, providing readers with a lucid understanding of RC’s hardware implementation and fostering innovative designs for in-sensor RC systems. Lastly, we identify prevailing challenges and suggest viable solutions, paving the way for future advancements in in-sensor RC technology.

Abstract Autonomous one‐shot on‐the‐fly learning copes with the high privacy, small dataset, and in‐stream data at the edge. Implementing such learning on digital hardware suffers from the well‐known von‐Neumann and scaling bottlenecks. The optical neural networks featuring large parallelism, low latency, and high efficiency offer a promising solution. However, ex‐situ training of conventional optical networks, where optical path configuration and deep learning model optimization are separated, incurs hardware, energy and time overheads, and defeats the advantages in edge learning. Here, we introduced a bio‐inspired material‐algorithm co‐design to construct a hydrogel‐based optical Willshaw model (HOWM), manifesting Hebbian‐rule‐based structural plasticity for simultaneous optical path configuration and deep learning model optimization thanks to the underlying opto‐chemical reactions. We first employed the HOWM as an all optical in‐sensor AI processor for one‐shot pattern classification, association and denoising. We then leveraged HOWM to function as a ternary content addressable memory (TCAM) of an optical memory augmented neural network (MANN) for one‐shot learning the Omniglot dataset. The HOWM empowered one‐shot on‐the‐fly edge learning leads to 1000× boost of energy efficiency and 10× boost of speed, which paves the way for the next‐generation autonomous, efficient, and affordable smart edge systems.

The rapid development of neural networks has led to tremendous applications in image segmentation, speech recognition, and medical image diagnosis, etc. Among various hardware implementations of neural networks, silicon photonics is considered one of the most promising approaches due to its CMOS compatibility, accessible integration platforms, mature fabrication techniques, and abundant optical components. In addition, neuromorphic computing based on silicon photonics can provide massively parallel processing and high-speed operations with low power consumption, thus enabling further exploration of neural networks. Here, we focused on the development of neuromorphic computing based on silicon photonics, introducing this field from the perspective of electronic–photonic co-design and presenting the architecture and algorithm theory. Finally, we discussed the prospects and challenges of neuromorphic silicon photonics.