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. The magnetic switching that occurs around and below the antenna is imaged using resonant X-ray holography and magnetic circular dichroism. The results not only show the feasibility of controllable switching with antenna assistance but also demonstrate the highly inhomogeneous nature of the switching process, which is attributed to the process depending on the material's heterogeneity.

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. The successful demonstration is supported by implementing new functions in crossbars, including the crossbar-based content-addressable memory and locality sensitive hashing exploiting the intrinsic stochasticity of memristor devices. Simulations show that such an implementation can be efficiently scaled up for one-shot learning on more complex tasks. The successful demonstration paves the way for practical on-device lifelong learning and opens possibilities for novel attention-based algorithms that were not possible in conventional 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. Here, we propose for the first time to use the analog CAM as an in-memory computational primitive to accelerate tree-based model inference. We demonstrate an efficient mapping algorithm leveraging the new analog CAM capabilities such that each root to leaf path of a Decision Tree is programmed into a row. This new in-memory compute concept for enables few-cycle model inference, dramatically increasing 103 × the throughput over conventional approaches.

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. We propose a new analog content-addressable memory concept and circuit to overcome these limitations by utilizing the analog conductance tunability of memristors. Our analog content-addressable memory stores data within the programmable conductance and can take as input either analog or digital search values. Experimental demonstrations, scaled simulations and analysis show that our analog content-addressable memory can reduce area and power consumption, which enables the acceleration of existing applications, but also new computing application areas.

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. Here, programming and control of memristors across an 86 × 12 memristor ternary CAM (TCAM) array integrated with CMOS are demonstrated, and parameter tradeoffs for optimizing speed and search margin are evaluated. In addition to smaller area, this memristor TCAM results in significantly lower power due to very low programmable conductance states, motivating CAM use in a wider range of computational applications than conventional TCAMs are confined to today. Finally, the first experimental demonstration of two computational models in memristor TCAM arrays is reported: regular expression matching in a finite state machine for network security intrusion detection and definable inexact pattern matching in a Levenshtein automata for genomic sequencing.

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. Single-layer neural network inference is performed in these arrays, and the performance compared to a digital approach is assessed. Memristor computing system used here reaches a VMM accuracy equivalent of 6 bits, and an 89.9% recognition accuracy is achieved for the 10k MNIST handwritten digit test set. Forecasts show that with integrated (on chip) and scaled memristors, a computational efficiency greater than 100 trillion operations per second per Watt is possible.

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. The excited states are stable over time as long as a voltage is applied to the device and have a higher conductance than the stable relaxed state. Experimental data on the time and voltage dependence of the excitation and decay are presented for Ta/TaOx/Pt and Ta/ZrOx/Pt devices. The effect is not limited to one oxide or electrode material but is observed with different magnitudes (up to 10× current change) in several oxide systems. These observations describe an additional state variable of the memristive system that is controlled in a highly polarity dependent manner.

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.

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. These results extend previous observations on 2D coated glass coverslips. We find that the morphology of growth cones is very different in 3D than in 2D, and that this difference suggests that the filopodia play a key role in optical guidance. This powerful, flexible, non-contact guidance technique has potentially broad applications in tissues and engineered environments.