Multiplexing in photonics as a resource for optical ternary content-addressable memory functionality.

In this paper, we combine a Content-Addressable Memory (CAM) encoding scheme previously proposed for analog electronic CAMs (E-CAMs) with optical multiplexing techniques to create two new photonic CAM architectures-wavelength-division multiplexing (WDM) optical ternary CAM (O-TCAM) and time-division multiplexing (TDM) O-TCAM. As an example, we show how these two O-TCAM schemes can be implemented by performing minor modifications in microring-based silicon photonic (SiPh) circuits originally optimized for exascale interconnects. Here, our SiPh O-TCAM designs include not only the actual search engine, but also the transmitter circuits.

Experimentally validated memristive memory augmented neural network with efficient hashing and similarity search.

Lifelong on-device learning is a key challenge for machine intelligence, and this requires learning from few, often single, samples. Memory-augmented neural networks have been proposed to achieve the goal, but the memory module must be stored in off-chip memory, heavily limiting the practical use. In this work, we experimentally validated that all different structures in the memory-augmented neural network can be implemented in a fully integrated memristive crossbar platform with an accuracy that closely matches digital hardware.

Tree-based machine learning performed in-memory with memristive analog CAM.

Tree-based machine learning techniques, such as Decision Trees and Random Forests, are top performers in several domains as they do well with limited training datasets and offer improved interpretability compared to Deep Neural Networks (DNN). However, these models are difficult to optimize for fast inference at scale without accuracy loss in von Neumann architectures due to non-uniform memory access patterns. Recently, we proposed a novel analog content addressable memory (CAM) based on emerging memristor devices for fast look-up table operations.

In-Memory Computing with Memristor Content Addressable Memories for Pattern Matching.

The dramatic rise of data-intensive workloads has revived application-specific computational hardware for continuing speed and power improvements, frequently achieved by limiting data movement and implementing "in-memory computation". However, conventional complementary metal oxide semiconductor (CMOS) circuit designs can still suffer low power efficiency, motivating designs leveraging nonvolatile resistive random access memory (ReRAM), and with many studies focusing on crossbar circuit architectures. Another circuit primitive-content addressable memory (CAM)-shows great promise for mapping a diverse range of computational models for in-memory computation, with recent ReRAM-CAM designs proposed but few experimentally demonstrated.

Analog content-addressable memories with memristors.

A content-addressable memory compares an input search word against all rows of stored words in an array in a highly parallel manner. While supplying a very powerful functionality for many applications in pattern matching and search, it suffers from large area, cost and power consumption, limiting its use. Past improvements have been realized by using memristors to replace the static random-access memory cell in conventional designs, but employ similar schemes based only on binary or ternary states for storage and search.

Memristor-Based Analog Computation and Neural Network Classification with a Dot Product Engine.

Using memristor crossbar arrays to accelerate computations is a promising approach to efficiently implement algorithms in deep neural networks. Early demonstrations, however, are limited to simulations or small-scale problems primarily due to materials and device challenges that limit the size of the memristor crossbar arrays that can be reliably programmed to stable and analog values, which is the focus of the current work. High-precision analog tuning and control of memristor cells across a 128 × 64 array is demonstrated, and the resulting vector matrix multiplication (VMM) computing precision is evaluated.

Volatile HRS asymmetry and subloops in resistive switching oxides.

Current-voltage characteristics of oxide-based resistive switching memories often show a pronounced asymmetry with respect to the voltage polarity in the high resistive state (HRS), where the HRS after the RESET is more conducting than the one before the SET. Here, we report that most of this HRS asymmetry is a volatile effect as the HRS obtained from a read operation differs from the one taken from the switching cycle at identical polarity and voltages. Transitions between the relaxed and the volatile excited states can be achieved via voltage sweeps, which are named subloops.

Direct Observation of Localized Radial Oxygen Migration in Functioning Tantalum Oxide Memristors.

Oxygen migration in tantalum oxide, a promising next-generation storage material, is studied using in operando X-ray absorption spectromicroscopy. This approach allows a physical description of the evolution of conduction channel and eventual device failure. The observed ring-like patterns of oxygen concentration are modeled using thermophoretic forces and Fick diffusion, establishing the critical role of temperature-driven oxygen migration.

Nanoscale Confinement of All-Optical Magnetic Switching in TbFeCo--Competition with Nanoscale Heterogeneity.

Single femtosecond optical laser pulses, of sufficient intensity, are demonstrated to reverse magnetization in a process known as all-optical switching. Gold two-wire antennas are placed on the all-optical switching film TbFeCo. These structures are resonant with the optical field, and they create a field enhancement in the near-field which confines the area where optical switching can occur.

Optical neuronal guidance in three-dimensional matrices.

We demonstrate effective guidance of neurites extending from PC12 cells in a three-dimensional collagen matrix using a focused infrared laser. Processes can be redirected in an arbitrarily chosen direction in the imaging plane in approximately 30 min with an 80% success rate. In addition, the application of the laser beam significantly increases the rate of neurite outgrowth.