A crossbar array of magnetoresistive memory devices for in-memory computing.

Implementations of artificial neural networks that borrow analogue techniques could potentially offer low-power alternatives to fully digital approaches1-3. One notable example is in-memory computing based on crossbar arrays of non-volatile memories4-7 that execute, in an analogue manner, multiply-accumulate operations prevalent in artificial neural networks. Various non-volatile memories-including resistive memory8-13, phase-change memory14,15 and flash memory16-19-have been used for such approaches. However, it remains challenging to develop a crossbar array of spin-transfer-torque magnetoresistive random-access memory (MRAM)20-22,  despite the technology's practical advantages such as endurance and large-scale commercialization5. The difficulty stems from the low resistance of MRAM, which would result in large power consumption in a conventional crossbar array that uses current summation for analogue multiply-accumulate operations. Here we report a 64 × 64 crossbar array based on MRAM cells that overcomes the low-resistance issue with an architecture that uses resistance summation for analogue multiply-accumulate operations. The array is integrated with readout electronics in 28-nanometre complementary metal-oxide-semiconductor technology. Using this array, a two-layer perceptron is implemented to classify 10,000 Modified National Institute of Standards and Technology digits with an accuracy of 93.23 per cent (software baseline: 95.24 per cent). In an emulation of a deeper, eight-layer Visual Geometry Group-8 neural network with measured errors, the classification accuracy improves to 98.86 per cent (software baseline: 99.28 per cent). We also use the array to implement a single layer in a ten-layer neural network to realize face detection with an accuracy of 93.4 per cent.

Always-On Sub-Microwatt Spiking Neural Network Based on Spike-Driven Clock- and Power-Gating for an Ultra-Low-Power Intelligent Device.

This paper presents a novel spiking neural network (SNN) classifier architecture for enabling always-on artificial intelligent (AI) functions, such as keyword spotting (KWS) and visual wake-up, in ultra-low-power internet-of-things (IoT) devices. Such always-on hardware tends to dominate the power efficiency of an IoT device and therefore it is paramount to minimize its power dissipation. A key observation is that the input signal to always-on hardware is typically sparse in time. This is a great opportunity that a SNN classifier can leverage because the switching activity and the power consumption of SNN hardware can scale with spike rate. To leverage this scalability, the proposed SNN classifier architecture employs event-driven architecture, especially fine-grained clock generation and gating and fine-grained power gating, to obtain very low static power dissipation. The prototype is fabricated in 65 nm CMOS and occupies an area of 1.99 mm2. At 0.52 V supply voltage, it consumes 75 nW at no input activity and less than 300 nW at 100% input activity. It still maintains competitive inference accuracy for KWS and other always-on classification workloads. The prototype achieved a power consumption reduction of over three orders of magnitude compared to the state-of-the-art for SNN hardware and of about 2.3X compared to the state-of-the-art KWS hardware.

Metabolomics approach to risk assessment: methoxyclor exposure in rats.

The primary objective of this study was to develop exposure biomarkers that "correlate with the endocrine-disrupting effects induced by methoxyclor (MTC), an organochlorine pesticide, using" urinary (1)H nuclear magnetic resonance (NMR) spectral data. Exposure biomarkers play an important role in risk assessment. MTC is an environmental endocrine disruptor with estrogenic, anti-estrogenic, and anti-androgenic properties. A new approach of proton nuclear magnetic resonance ((1)H NMR) urinalysis using pattern recognition was proposed for exposure biomarkers of MTC in female rats. The endocrine disruptor was expected to induce estrogenic effects in a dose dependent manner which, was confirmed by the uterotrophic assay. MTC [50, 100, or 200 m g/kg/d, orally (p.o.) or subcutaneously (s.c.)] was administered to ovariectomized female Sprague-Dawley (SD) rats for 3 d consecutively and urine was collected every 24 h. The animals were sacrificed 24 h after the last dose. All animals treated orally with MTC showed a significant increase in uterine and vaginal weight at all doses. However, in the s.c. route, only a high dose of 200 mg MTC/kg induced a significant increase in uterine and vaginal weight. (1)H NMR spectroscopy revealed evident separate clustering between pre- and post-treatment groups using global metabolic profiling through principal component analysis (PCA) and partial least square (PLS) discrimination analysis (DA) after different exposure routes. With targeted profiling, the endogenous metabolites of acetate, alanine, benzoate, lactate, and glycine were selected as putative exposure biomarkers for MTC. Data suggest that the proposed putative exposure biomarkers may be useful in a risk assessment of the endocrine-disrupting effects produced by MTC.