Search NASA⌕ Search

Engineering topics

Xiao, T. Patrick

Publications and source records attributed to Xiao, T. Patrick.

Shape‐Dependent Multi‐Weight Magnetic Artificial Synapses for Neuromorphic Computing

Abstract In neuromorphic computing, artificial synapses provide a multi‐weight (MW) conductance state that is set based on inputs from neurons, analogous to the brain. Herein, artificial synapses based on magnetic materials that use a magnetic tunnel junction (MTJ) and a magnetic domain wall (DW) are explored. By fabricating lithographic notches in a DW track underneath a single MTJ, 3–5 stable resistance states that can be repeatably controlled electrically using spin‐orbit torque are achieved. The effect of geometry on the synapse behavior is explored, showing that a trapezoidal device has asymmetric weight updates with high controllability, while a rectangular device has higher stochasticity, but with stable resistance levels. The device data is input into neuromorphic computing simulators to show the usefulness of application‐specific synaptic functions. Implementing an artificial neural network (NN) applied to streamed Fashion‐MNIST data, the trapezoidal magnetic synapse can be used as a metaplastic function for efficient online learning. Implementing a convolutional NN for CIFAR‐100 image recognition, the rectangular magnetic synapse achieves near‐ideal inference accuracy, due to the stability of its resistance levels. This work shows MW magnetic synapses are a feasible technology for neuromorphic computing and provides design guidelines for emerging artificial synapse technologies.

Leonard, Thomas↗

Metaplastic and energy-efficient biocompatible graphene artificial synaptic transistors for enhanced accuracy neuromorphic computing

CMOS-based computing systems that employ the von Neumann architecture are relatively limited when it comes to parallel data storage and processing. In contrast, the human brain is a living computational signal processing unit that operates with extreme parallelism and energy efficiency. Although numerous neuromorphic electronic devices have emerged in the last decade, most of them are rigid or contain materials that are toxic to biological systems. In this work, we report on biocompatible bilayer graphene-based artificial synaptic transistors (BLAST) capable of mimicking synaptic behavior. The BLAST devices leverage a dry ion-selective membrane, enabling long-term potentiation, with ~50 aJ/µm 2 switching energy efficiency, at least an order of magnitude lower than previous reports on two-dimensional material-based artificial synapses. The devices show unique metaplasticity, a useful feature for generalizable deep neural networks, and we demonstrate that metaplastic BLASTs outperform ideal linear synapses in classic image classification tasks. With switching energy well below the 1 fJ energy estimated per biological synapse, the proposed devices are powerful candidates for bio-interfaced online learning, bridging the gap between artificial and biological neural networks.

97 MATHEMATICS AND COMPUTING↗

Analysis and mitigation of parasitic resistance effects for analog in-memory neural network acceleration

To support the increasing demands for efficient deep neural network processing, accelerators based on analog in-memory computation of matrix multiplication have recently gained significant attention for reducing the energy of neural network inference. However, analog processing within memory arrays must contend with the issue of parasitic voltage drops across the metal interconnects, which distort the results of the computation and limit the array size. This work analyzes how parasitic resistance affects the end-to-end inference accuracy of state-of-the-art convolutional neural networks, and comprehensively studies how various design decisions at the device, circuit, architecture, and algorithm levels affect the system's sensitivity to parasitic resistance effects. Here, a set of guidelines are provided for how to design analog accelerator hardware that is intrinsically robust to parasitic resistance, without any explicit compensation or re-training of the network parameters.

97 MATHEMATICS AND COMPUTING↗

A domain wall-magnetic tunnel junction artificial synapse with notched geometry for accurate and efficient training of deep neural networks

Inspired by the parallelism and efficiency of the brain, several candidates for artificial synapse devices have been developed for neuromorphic computing, yet a nonlinear and asymmetric synaptic response curve precludes their use for backpropagation, the foundation of modern supervised learning. Spintronic devices—which benefit from high endurance, low power consumption, low latency, and CMOS compatibility—are a promising technology for memory, and domain-wall magnetic tunnel junction (DW-MTJ) devices have been shown to implement synaptic functions such as long-term potentiation and spike-timing dependent plasticity. In this work, we propose a notched DW-MTJ synapse as a candidate for supervised learning. Using micromagnetic simulations at room temperature, we show that notched synapses ensure the non-volatility of the synaptic weight and allow for highly linear, symmetric, and reproducible weight updates using either spin transfer torque (STT) or spin–orbit torque (SOT) mechanisms of DW propagation. We use lookup tables constructed from micromagnetics simulations to model the training of neural networks built with DW-MTJ synapses on both the MNIST and Fashion-MNIST image classification tasks. Accounting for thermal noise and realistic process variations, the DW-MTJ devices achieve classification accuracy close to ideal floating-point updates using both STT and SOT devices at room temperature and at 400 K. Our work establishes the basis for a magnetic artificial synapse that can eventually lead to hardware neural networks with fully spintronic matrix operations implementing machine learning.

42 ENGINEERING↗

In situ Parallel Training of Analog Neural Network Using Electrochemical Random-Access Memory

In-memory computing based on non-volatile resistive memory can significantly improve the energy efficiency of artificial neural networks. However, accurate in situ training has been challenging due to the nonlinear and stochastic switching of the resistive memory elements. One promising analog memory is the electrochemical random-access memory (ECRAM), also known as the redox transistor. Its low write currents and linear switching properties across hundreds of analog states enable accurate and massively parallel updates of a full crossbar array, which yield rapid and energy-efficient training. While simulations predict that ECRAM based neural networks achieve high training accuracy at significantly higher energy efficiency than digital implementations, these predictions have not been experimentally achieved. In this work, we train a 3 × 3 array of ECRAM devices that learns to discriminate several elementary logic gates (AND, OR, NAND). We record the evolution of the network’s synaptic weights during parallel in situ (on-line) training, with outer product updates. Due to linear and reproducible device switching characteristics, our crossbar simulations not only accurately simulate the epochs to convergence, but also quantitatively capture the evolution of weights in individual devices. The implementation of the first in situ parallel training together with strong agreement with simulation results provides a significant advance toward developing ECRAM into larger crossbar arrays for artificial neural network accelerators, which could enable orders of magnitude improvements in energy efficiency of deep neural networks.

97 MATHEMATICS AND COMPUTING↗

Ultraefficient thermophotovoltaic power conversion by band-edge spectral filtering

Thermophotovoltaic power conversion utilizes thermal radiation from a local heat source to generate electricity in a photovoltaic cell. It was shown in recent years that the addition of a highly reflective rear mirror to a solar cell maximizes the extraction of luminescence. This, in turn, boosts the voltage, enabling the creation of record-breaking solar efficiency. Now we report that the rear mirror can be used to create thermophotovoltaic systems with unprecedented high thermophotovoltaic efficiency. This mirror reflects low-energy infrared photons back into the heat source, recovering their energy. Therefore, the rear mirror serves a dual function; boosting the voltage and reusing infrared thermal photons. This allows the possibility of a practical >50% efficient thermophotovoltaic system. Based on this reflective rear mirror concept, we report a thermophotovoltaic efficiency of 29.1 ± 0.4% at an emitter temperature of 1,207 °C.

14 SOLAR ENERGY↗

Pushing the Limits of Thermophotovoltaic Efficiency

We report power conversion efficiency of ~28% from a thermophotovoltaic device, employing the concept of photon regeneration. The regeneration is accomplished using photovoltaic band-edge as the spectral filter. This high efficiency is a direct consequence of enhanced sub-bandgap reflectivity of the device used. Our detail theoretical analysis shows that with further improvement in device geometry and material, it would be possible to achieve near 45% power conversion efficiency.

14 SOLAR ENERGY↗

Electroluminescent refrigeration by ultra-efficient GaAs light-emitting diodes

Electroluminescence—the conversion of electrons to photons in a light-emitting diode (LED)—can be used as a mechanism for refrigeration, provided that the LED has an exceptionally high quantum efficiency. We investigate the practical limits of present optoelectronic technology for cooling applications by optimizing a GaAs/GaInP double heterostructure LED. We develop a model of the design based on the physics of detailed balance and the methods of statistical ray optics, and predict an external luminescence efficiency of η ext = 97.7% at 263 K. To enhance the cooling coefficient of performance, we pair the refrigerated LED with a photovoltaic cell, which partially recovers the emitted optical energy as electricity. For applications near room temperature and moderate power densities (1.0–10 mW/cm 2 ), we project that an electroluminescent refrigerator can operate with up to 1.7× the coefficient of performance of thermoelectric coolers with ZT = 1, using the material quality in existing GaAs devices. We also predict superior cooling efficiency for cryogenic applications relative to both thermoelectric and laser cooling. Large improvements to these results are possible with optoelectronic devices that asymptotically approach unity luminescence efficiency.

36 MATERIALS SCIENCE↗