In-sensor computing can simultaneously output image information and recognition results through in-situ visual signal processing, which can greatly improve the efficiency of machine vision. However, in-sensor computing is challenging due to the requirement to controllably adjust the sensor’s photosensitivity. Herein, it is demonstrated a ternary cationic halide Cs0.05FA0.81MA0.14 Pb(I0.85Br0.15)3 (CsFAMA) perovskite, whose External quantum efficiency (EQE) value is above 80% in the entire visible region (400–750 nm), and peak responsibility value at 750 nm reaches 0.45 A/W. In addition, the device can achieve a 50-fold enhancement of the photoresponsibility under the same illumination by adjusting the internal ion migration and readout voltage. A proof-of-concept visually enhanced neural network system is demonstrated through the switchable photosensitivity of the perovskite sensor array, which can simultaneously optimize imaging and recognition results and improve object recognition accuracy by 17% in low-light environments.

No abstract

Summary This paper presents an output capacitor‐less low‐dropout regulator (LDO) with wide load capacitance and current ranges. A new Miller compensation technique called multipath double‐nested Miller compensation with Q‐reduction circuit is introduced to extend the ranges of the load capacitance and current. Besides, a multiple small‐gain stages technology is applied to improve the loop gain of the LDO, achieving better management accuracy. The proposed LDO was fabricated in a 130‐nm CMOS process. The measured maximum load capacitance can be extended to 4.7 nF, and the maximum load current is 80 mA. Moreover, the measured line regulation and load regulation are 4 mV/V and 0.154 mV/mA, respectively.

No abstract

SummaryThis brief proposes a new lightweight authenticated encryption algorithm SIMON‐GCM for Internet of Things (IoT) security, which realizes the combination of SIMON block cipher and Galois/Counter Mode (GCM). The designed SIMON circuit supports 128/192/256‐bit key size, which improves the flexibility and enlarges the range of applications. Moreover, the scheme of 32‐cycle Galois field (GF) multiplier in GF(2128) is adopted to effectively reduce the hardware cost of the Galois Hash (GHASH) function in GCM. At the same time, a finite state machine (FSM) is used to run the SIMON and GHASH modules in parallel, thus shortening the authenticated encryption time. The whole circuit is designed and implemented in field programmable gate array (FPGA) platforms. It is measured to yield a throughput of 32.4 Gbps when consuming 331 slices in Artix‐7. Compared with the existing authenticated encryption algorithms, the proposed algorithm achieves lower resource consumption and better flexibility.

Compared with the traditional memristor, it's more significant to research the multivalued memristor in improving the stability and reliability of memristive neural networks. Developing some multivalued memristor emulators is highly attractive since the fabrication and integration of the memristor are not mature at present. This work presents a behavioral‐level model of a general multivalued memristor FPGA that exhibits continuous or discrete behavior, similar to electrochemical metallization memories. The proposed solution has been successfully synthesized and verified on a Xilinx ZYNQ‐7000 FPGA XQ7Z020 with less than 1% hardware utilization. Additionally, to test the synaptic function of the memristor model in artificial neural networks, this paper constructs a quantized artificial neural network based on eight‐valued memristors in FPGA. In the training of the neural network, the pixel values of the images and the network weights are quantized and then mapped to the input voltage and conductance respectively of the memristor during the forward propagation. The experimental results show that the memristive network circuit achieves 92.8% recognition accuracy for 10,000 MNIST images.

No abstract

No abstract