The memristor neurons built with two memristors can be used to mimics many dynamical behaviours of a biological neuron. Firstly, the dynamic operating conditions of memristor neurons and their transformation boundaries between the spiking and the bursting are comprehensively investigated. Then, the underlying mechanism of bursting is analysed and the controllability of the number of spikes in each burst period is demonstrated under proper input voltage and input resistor. Final, numbers of spikes per period is recognized as neuron information carries and shown to enable pattern recognition and information transmitting. These results show a promising approach for the efficient use of neuristor in the construction of neural networks.

As one of the most promising emerging non-volatile memory (NVM) technologies, spin-transfer torque magnetic random access memory (STT-MRAM) has attracted significant research attention due to several features such as high density, zero standby leakage, and nearly unlimited endurance. However, a high-quality test solution is required prior to the commercialization of STT-MRAM. In this paper, we present all STT-MRAM failure mechanisms: manufacturing defects, extreme process variations, magnetic coupling, STT-switching stochasticity, and thermal fluctuation. The resultant fault models including permanent faults and transient faults are classified and discussed. Moreover, the limited test algorithms and design-for-testability (DfT) designs proposed in the literature are also covered. It is clear that test solutions for STT-MRAMs are far from well established yet, especially when considering a defective part per billion (DPPB) level requirement. We present the main challenges on the STT-MRAM testing topic at three levels: failure mechanisms, fault modeling, and test/DfT designs.

Using optimal phasor measurement unit placement as a prototypical problem, we assess the computational viability of the current generation D-Wave Systems 2000Q quantum annealer for power systems design problems. We reformulate minimum dominating set for the annealer hardware, solve the reformulation for a standard set of IEEE test systems, and benchmark solution quality and time to solution against the CPLEX Optimizer and simulated annealing. For some problem instances the 2000Q outpaces CPLEX. For instances where the 2000Q underperforms with respect to CPLEX and simulated annealing, we suggest hardware improvements for the next generation of quantum annealers.

Magnetic random-access memory (MRAM) is a promising memory technology due to its high density, non-volatility, and high endurance. However, achieving high memory fidelity incurs significant write-energy costs, which should be reduced for large-scale deployment of MRAMs. In this paper, we formulate an optimization problem for maximizing the memory fidelity given energy constraints, and propose a biconvex optimization approach to solve it. The basic idea is to allocate non-uniform write pulses depending on the importance of each bit position. The fidelity measure we consider is minimum mean squared error (MSE), for which we propose an iterative water-filling algorithm. Although the iterative algorithm does not guarantee global optimality, we can choose a proper starting point that decreases the MSE exponentially and guarantees fast convergence. For an 8-bit accessed word, the proposed algorithm reduces the MSE by a factor of 21.

Due to extremely low power consumption, backscatter has become the transmission mechanism of choice for battery-free devices that operate on harvested energy. However, a limitation of recent backscatter systems is that the communication range scales with the strength of the ambient carrier signal(ACS). This means that to achieve a long range, a backscatter tag needs to reflect a strong ACS, which in practice means that it needs to be close to an ACS emitter. We present TunnelScatter, a mechanism that overcomes this limitation. TunnelScatter uses a tunnel diode-based radio frequency oscillator to enable transmissions when there is no ACS, and the same oscillator as a reflection amplifier to support backscatter transmissions when the ACS is weak. Our results show that even without an ACS, TunnelScatter is able to transmit through several walls covering a distance of 18 meter while consuming a peak biasing power of 57 microwatts. Based on TunnelScatter, we design battery-free sensor tags, called TunnelTags, that can sense physical phenomena and transmit them using the TunnelScatter mechanism.

The increasing popularity of machine learning solutions puts increasing restrictions on this field if it is to penetrate more aspects of life. In particular, energy efficiency and speed of operation is crucial, inter alia in portable medical devices. The Reservoir Computing (RC) paradigm poses as a solution to these issues through foundation of its operation: the reservoir of states. Adequate separation of input information translated into the internal state of the reservoir, whose connections do not need to be trained, allow to simplify the readout layer thus significantly accelerating the operation of the system. In this brief review article, the theoretical basis of RC was first described, followed by a description of its individual variants, their development and state-of-the-art applications in chemical sensing and metrology: detection of impedance changes and ion sensing. Presented results indicate applicability of reservoir computing for sensing and validating the SWEET algorithm experimentally.

In order to support near-term applications of quantum computing, a new compute paradigm has emerged--the quantum-classical cloud--in which quantum computers (QPUs) work in tandem with classical computers (CPUs) via a shared cloud infrastructure. In this work, we enumerate the architectural requirements of a quantum-classical cloud platform, and present a framework for benchmarking its runtime performance. In addition, we walk through two platform-level enhancements, parametric compilation and active qubit reset, that specifically optimize a quantum-classical architecture to support variational hybrid algorithms (VHAs), the most promising applications of near-term quantum hardware. Finally, we show that integrating these two features into the Rigetti Quantum Cloud Services (QCS) platform results in considerable improvements to the latencies that govern algorithm runtime.

Crosstalk is a major source of noise in Noisy Intermediate-Scale Quantum (NISQ) systems and is a fundamental challenge for hardware design. When multiple instructions are executed in parallel, crosstalk between the instructions can corrupt the quantum state and lead to incorrect program execution. Our goal is to mitigate the application impact of crosstalk noise through software techniques. This requires (i) accurate characterization of hardware crosstalk, and (ii) intelligent instruction scheduling to serialize the affected operations. Since crosstalk characterization is computationally expensive, we develop optimizations which reduce the characterization overhead. On three 20-qubit IBMQ systems, we demonstrate two orders of magnitude reduction in characterization time (compute time on the QC device) compared to all-pairs crosstalk measurements. Informed by these characterization, we develop a scheduler that judiciously serializes high crosstalk instructions balancing the need to mitigate crosstalk and exponential decoherence errors from serialization. On real-system runs on three IBMQ systems, our scheduler improves the error rate of application circuits by up to 5.6x, compared to the IBM instruction scheduler and offers near-optimal crosstalk mitigation in practice. In a broader picture, the difficulty of mitigating crosstalk has recently driven QC vendors to move towards sparser qubit connectivity or disabling nearby operations entirely in hardware, which can be detrimental to performance. Our work makes the case for software mitigation of crosstalk errors.

This paper considers implementation of artificial neural networks (ANNs) using molecular computing and DNA based on fractional coding. Prior work had addressed molecular two-layer ANNs with binary inputs and arbitrary weights. In prior work using fractional coding, a simple molecular perceptron that computes sigmoid of scaled weighted sum of the inputs was presented where the inputs and the weights lie between [-1, 1]. Even for computing the perceptron, the prior approach suffers from two major limitations. First, it cannot compute the sigmoid of the weighted sum, but only the sigmoid of the scaled weighted sum. Second, many machine learning applications require the coefficients to be arbitrarily positive and negative numbers that are not bounded between [-1, 1]; such numbers cannot be handled by the prior perceptron using fractional coding. This paper makes four contributions. First molecular perceptrons that can handle arbitrary weights and can compute sigmoid of the weighted sums are presented. Thus, these molecular perceptrons are ideal for regression applications and multi-layer ANNs. A new molecular divider is introduced and is used to compute sigmoid(ax) where a > 1. Second, based on fractional coding, a molecular artificial neural network (ANN) with one hidden layer is presented. Third, a trained ANN classifier with one hidden layer from seizure prediction application from electroencephalogram is mapped to molecular reactions and DNA and their performances are presented. Fourth, molecular activation functions for rectified linear unit (ReLU) and softmax are also presented.

This paper describes a novel approach to synthesize molecular reactions to train a perceptron, i.e., a single-layered neural network, with sigmoidal activation function. The approach is based on fractional coding where a variable is represented by two molecules. The synergy between fractional coding in molecular computing and stochastic logic implementations in electronic computing is key to translating known stochastic logic circuits to molecular computing. In prior work, a DNA perceptron with bipolar inputs and unipolar output was proposed for inference. The focus of this paper is on synthesis of molecular reactions for training of the DNA perceptron. A new molecular scaler that performs multiplication by a factor greater than 1 is proposed based on fractional coding. The training of the perceptron proposed in this paper is based on a modified backpropagation equation as the exact equation cannot be easily mapped to molecular reactions using fractional coding.

Photonic waveguides are prime candidates for integrated and parallel photonic interconnects. Such interconnects correspond to large-scale vector matrix products, which are at the heart of neural network computation. However, parallel interconnect circuits realized in two dimensions, for example by lithography, are strongly limited in size due to disadvantageous scaling. We use three dimensional (3D) printed photonic waveguides to overcome this limitation. 3D optical-couplers with fractal topology efficiently connect large numbers of input and output channels, and we show that the substrate's footprint area scales linearly. Going beyond simple couplers, we introduce functional circuits for discrete spatial filters identical to those used in deep convolutional neural networks.

In the present paper, we report on the switching dynamics of both single and coupled VO2-based oscillators, with resistive and capacitive coupling, and explore the capability of their application in oscillatory neural networks. Based on these results, we further select an adequate SPICE model to describe the modes of operation of coupled oscillator circuits. Physical mechanisms influencing the time of forward and reverse electrical switching, that determine the applicability limits of the proposed model, are identified. For the resistive coupling, it is shown that synchronization takes place at a certain value of the coupling resistance, though it is unstable and a synchronization failure occurs periodically. For the capacitive coupling, two synchronization modes, with weak and strong coupling, are found. The transition between these modes is accompanied by chaotic oscillations. A decrease in the width of the spectrum harmonics in the weak-coupling mode, and its increase in the strong-coupling one, is detected. The dependences of frequencies and phase differences of the coupled oscillatory circuits on the coupling capacitance are found. Examples of operation of coupled VO2 oscillators as a central pattern generator are demonstrated.

Persistent Memory (PM), as already available e.g. with Intel Optane DC Persistent Memory, represents a very promising, next generation memory solution with a significant impact on database architectures. Several data structures for this new technology and its properties have already been proposed. However, primarily merely complete structures were presented and evaluated hiding the impact of the individual ideas and PM characteristics. Therefore, in this paper, we disassemble the structures presented so far, identify their underlying design primitives, and assign them to appropriate design goals regarding PM. As a result of our comprehensive experiments on real PM hardware, we were able to reveal the trade-offs of the primitives at the micro level. From this, performance profiles could be derived for selected primitives. With these it is possible to precisely identify their best use cases as well as vulnerabilities. Beside our general insights regarding PM-based data structure design, we also discovered new promising combinations not considered in the literature so far.

Current remote patient monitoring (RPM) systems are fully reliant on the Internet. However, complete reliance on Internet connectivity is impractical in rural and remote environments where modern infrastructure is often lacking, power outages are frequent, and/or network connectivity is sparse (e.g. rural communities, mountainous regions of Appalachia, American Indian reservations, developing countries, and natural disaster situations). This paper proposes augmenting intermittent Internet with opportunistic communication to leverage the social behaviors of patients, caregivers, and community members to facilitate out-of-range monitoring of patients via Bluetooth 5 during intermittent network connectivity in rural communities. The architecture is evaluated for Owingsville, KY using U.S. Census Bureau, the National Cancer Institute's, and IPUMS-ATUS sample data, and is compared against a delay tolerant RPM case that is completely disconnected from the Internet. The findings show that with only 0.30 rural adult population participation, the architecture can deliver 0.95 of non-emergency medical information with an average delivery latency of approximately 13 hours.

The emerging mobile devices in this era of internet-of-things (IoT) require a dedicated processor to enable computationally intensive applications such as neuromorphic computing and signal processing. Vector-by-matrix multiplication (VMM) is the most prominent operation in these applications. Therefore, there is a critical need for compact and ultralow-power VMM blocks to perform resource-intensive low-to-moderate precision computations. To this end, in this work, for the first time, we propose a time-domain mixed-signal VMM exploiting a modified configuration of 1MOSFET-1RRAM (1T-1R) array. The proposed VMM overcomes the energy inefficiency of the current-mode VMM approaches based on RRAMs. A rigorous analysis of the different non-ideal factors affecting the computational precision indicates that the non-negligible minimum cell currents, channel length modulation (CLM) and drain-induced barrier lowering (DIBL) are the dominant mechanisms degrading the precision of the proposed VMM. Our results also indicate that there exists a trade-off between the computational precision, dynamic range, and the area- and energy-efficiency of the proposed VMM approach. Therefore, we provide the necessary design guidelines for optimizing the performance. Our preliminary results show that an effective computational precision of 6-bits is achievable owing to an inherent compensation effect in the modified 1T-1R blocks. Furthermore, a 4-bit 200x200 VMM utilizing the proposed approach exhibits a significantly high energy efficiency of ~1.5 POps/J and a throughput of 2.5 TOps/s including the contribution from the input/output (I/O) circuitry.

We explore a prototype of an oscillatory neural network (ONN) based on vanadium dioxide switching devices. The model system under study represents two oscillators based on thermally coupled VO2 switches. Numerical simulation shows that the effective action radius RTC of coupling depends both on the total energy released during switching and on the average power. It is experimentally and numerically proved that the temperature change dT commences almost synchronously with the released power peak and T-coupling reveals itself up to a frequency of about 10 kHz. For the studied switching structure configuration, the RTC value varies over a wide range from 4 to 45 mkm, depending on the external circuit capacitance C and resistance Ri, but the variation of Ri is more promising from the practical viewpoint. In the case of a "weak" coupling, synchronization is accompanied by attraction effect and decrease of the main spectra harmonics width. In the case of a "strong" coupling, the number of effects increases, synchronization can occur on subharmonics resulting in multilevel stable synchronization of two oscillators. An advanced algorithm for synchronization efficiency and subharmonic ratio calculation is proposed. It is shown that of the two oscillators the leading one is that with a higher main frequency, and, in addition, the frequency stabilization effect is observed. Also, in the case of a strong thermal coupling, the limit of the supply current parameters, for which the oscillations exist, expands by ~ 10 %. The obtained results have a universal character and open up a new kind of coupling in ONNs, namely, T-coupling, which allows for easy transition from 2D to 3D integration. The effect of subharmonic synchronization hold promise for application in classification and pattern recognition.

The D-Wave quantum annealer has emerged as a novel computational architecture that is attracting significant interest, but there have been only a few practical algorithms exploiting the power of quantum annealers. Here we present a model predictive control (MPC) algorithm using a quantum annealer for a system allowing a finite number of input values. Such an MPC problem is classified as a non-deterministic polynomial-time-hard combinatorial problem, and thus real-time sequential optimization is difficult to obtain with conventional computational systems. We circumvent this difficulty by converting the original MPC problem into a quadratic unconstrained binary optimization problem, which is then solved by the D-Wave quantum annealer. Two practical applications, namely stabilization of a spring-mass-damper system and dynamic audio quantization, are demonstrated. For both, the D-Wave method exhibits better performance than the classical simulated annealing method. Our results suggest new applications of quantum annealers in the direction of dynamic control problems.

For the benefit of designing scalable, fault resistant optical neural networks (ONNs), we investigate the effects architectural designs have on the ONNs' robustness to imprecise components. We train two ONNs -- one with a more tunable design (GridNet) and one with better fault tolerance (FFTNet) -- to classify handwritten digits. When simulated without any imperfections, GridNet yields a better accuracy (~98%) than FFTNet (~95%). However, under a small amount of error in their photonic components, the more fault tolerant FFTNet overtakes GridNet. We further provide thorough quantitative and qualitative analyses of ONNs' sensitivity to varying levels and types of imprecisions. Our results offer guidelines for the principled design of fault-tolerant ONNs as well as a foundation for further research.

The abstract mathematical rules of artificial neural network (ANN) are implemented through computation using electronic computers, photonics and in-vitro DNA computation. Here we demonstrate the physical realization of ANN in living bacterial cells. We created a single layer ANN using engineered bacteria, where a single bacterium works as an artificial neuron and demonstrated a 2-to-4 decoder and a 1-to-2 de-multiplexer for processing chemical signals. The inputs were extracellular chemical signals, which linearly combined and got processed through a non-linear log-sigmoid activation function to produce fluorescent protein outputs. The activation function was generated by synthetic genetic circuits, and for each artificial neuron, the weight and bias values were adjusted manually by engineering the molecular interactions within the bacterial neuron to represent a specific logical function. The artificial bacterial neurons were connected as ANN architectures to implement a 2-to-4 chemical decoder and a 1-to-2 chemical de-multiplexer. To our knowledge, this is the first ANN created by artificial bacterial neurons. Thus, it may open up a new direction in ANN research, where engineered biological cells can be used as ANN enabled hardware.

During the last few years, intensive research efforts are being done in the field of brain interfaces to extract neuro-information from the signals representing neuronal activities in the human brain. A recent development of these interfaces is capable of direct communication between animals' brains, enabling direct brain-to-brain communication. Although these results are new and the experimental scenario simple, the fast development in neuroscience, and information and communication technologies indicate the potential of new scenarios for wireless communications between brains. Depending of the specific kind of neuro-activity to be communicated, the brain-to-brain link shall follow strict requirements of high data rates, low-latency, and reliable communication. In this paper we highlight key beyond 5G technologies that potentially will support this promising approach.

Intelligent reflecting surface (IRS) is a cost-effective solution for achieving high spectrum and energy efficiency in future wireless networks by leveraging massive low-cost passive elements that are able to reflect the signals with adjustable phase shifts. Prior works on IRS mainly consider continuous phase shifts at reflecting elements, which are practically difficult to implement due to the hardware limitation. In contrast, we study in this paper an IRS-aided wireless network, where an IRS with only a finite number of phase shifts at each element is deployed to assist in the communication from a multi-antenna access point (AP) to multiple single-antenna users. We aim to minimize the transmit power at the AP by jointly optimizing the continuous transmit precoding at the AP and the discrete reflect phase shifts at the IRS, subject to a given set of minimum signal-to-interference-plus-noise ratio (SINR) constraints at the user receivers. The considered problem is shown to be a mixed-integer non-linear program (MINLP) and thus is difficult to solve in general. To tackle this problem, we first study the single-user case with one user assisted by the IRS and propose both optimal and suboptimal algorithms for solving it. Besides, we analytically show that as compared to the ideal case with continuous phase shifts, the IRS with discrete phase shifts achieves the same squared power gain in terms of asymptotically large number of reflecting elements, while a constant proportional power loss is incurred that depends only on the number of phase-shift levels. The proposed designs for the single-user case are also extended to the general setup with multiple users among which some are aided by the IRS. Simulation results verify our performance analysis as well as the effectiveness of our proposed designs as compared to various benchmark schemes.

Probabilistic machine learning enabled by the Bayesian formulation has recently gained significant attention in the domain of automated reasoning and decision-making. While impressive strides have been made recently to scale up the performance of deep Bayesian neural networks, they have been primarily standalone software efforts without any regard to the underlying hardware implementation. In this paper, we propose an "All-Spin" Bayesian Neural Network where the underlying spintronic hardware provides a better match to the Bayesian computing models. To the best of our knowledge, this is the first exploration of a Bayesian neural hardware accelerator enabled by emerging post-CMOS technologies. We develop an experimentally calibrated device-circuit-algorithm co-simulation framework and demonstrate $24\times$ reduction in energy consumption against an iso-network CMOS baseline implementation.

Uncertainty plays a key role in real-time machine learning. As a significant shift from standard deep networks, which does not consider any uncertainty formulation during its training or inference, Bayesian deep networks are being currently investigated where the network is envisaged as an ensemble of plausible models learnt by the Bayes' formulation in response to uncertainties in sensory data. Bayesian deep networks consider each synaptic weight as a sample drawn from a probability distribution with learnt mean and variance. This paper elaborates on a hardware design that exploits cycle-to-cycle variability of oxide based Resistive Random Access Memories (RRAMs) as a means to realize such a probabilistic sampling function, instead of viewing it as a disadvantage.