No abstract

This paper presents a novel method to fabricate temperature sensor arrays by dispensing a graphite-polydimethylsiloxane composite on flexible polyimide films. The fabricated temperature sensor array has 64 sensing cells in a 4 × 4 cm2 area. The sensor array can be used as humanoid artificial skin for sensation system of robots. Interdigitated copper electrodes were patterned on the flexible polyimide substrate for determining the resistivity change of the composites subjected to ambient temperature variations. Polydimethylsiloxane was used as the matrix. Composites of different graphite volume fractions for large dynamic range from 30 °C to 110 °C have been investigated. Our experiments showed that graphite powder provided the composite high temperature sensitivity. The fabricated temperature sensor array has been tested. The detected temperature contours are in good agreement with the shapes and magnitudes of different heat sources.

Non-volatile computing-in-memory macros that are based on two-dimensional arrays of memristors are of use in the development of artificial intelligence edge devices. Scaling such systems to three-dimensional arrays could provide higher parallelism, capacity and density for the necessary vector–matrix multiplication operations. However, scaling to three dimensions is challenging due to manufacturing and device variability issues. Here we report a two-kilobit non-volatile computing-in-memory macro that is based on a three-dimensional vertical resistive random-access memory fabricated using a 55 nm complementary metal–oxide–semiconductor process. Our macro can perform 3D vector–matrix multiplication operations with an energy efficiency of 8.32 tera-operations per second per watt when the input, weight and output data are 8, 9 and 22 bits, respectively, and the bit density is 58.2 bit µm–2. We show that the macro offers more accurate brain MRI edge detection and improved inference accuracy on the CIFAR-10 dataset than conventional methods.

No abstract

No abstract