Spiking Neural Network Pressure Sensor.

Von Neumann architecture requires information to be encoded as numerical values. For that reason, artificial neural networks running on computers require the data coming from sensors to be discretized. Other network architectures that more closely mimic biological neural networks (e.g., spiking neural networks) can be simulated on von Neumann architecture, but more important, they can also be executed on dedicated electrical circuits having orders of magnitude less power consumption. Unfortunately, input signal conditioning and encoding are usually not supported by such circuits, so a separate module consisting of an analog-to-digital converter, encoder, and transmitter is required. The aim of this article is to propose a sensor architecture, the output signal of which can be directly connected to the input of a spiking neural network. We demonstrate that the output signal is a valid spike source for the Izhikevich model neurons, ensuring the proper operation of a number of neurocomputational features. The advantages are clear: much lower power consumption, smaller area, and a less complex electronic circuit. The main disadvantage is that sensor characteristics somehow limit the parameters of applicable spiking neurons. The proposed architecture is illustrated by a case study involving a capacitive pressure sensor circuit, which is compatible with most of the neurocomputational properties of the Izhikevich neuron model. The sensor itself is characterized by very low power consumption: it draws only 3.49 µA at 3.3 V.

Multi-state MRAM cells for hardware neuromorphic computing.

Magnetic tunnel junctions (MTJ) have been successfully applied in various sensing application and digital information storage technologies. Currently, a number of new potential applications of MTJs are being actively studied, including high-frequency electronics, energy harvesting or random number generators. Recently, MTJs have been also proposed in designs of new platforms for unconventional or bio-inspired computing. In the current work, we present a complete hardware implementation design of a neural computing device that incorporates serially connected MTJs forming a multi-state memory cell can be used in a hardware implementation of a neural computing device. The main purpose of the multi-cell is the formation of quantized weights in the network, which can be programmed using the proposed electronic circuit. Multi-cells are connected to a CMOS-based summing amplifier and a sigmoid function generator, forming an artificial neuron. The operation of the designed network is tested using a recognition of hand-written digits in 20 [Formula: see text] 20 pixels matrix and shows detection ratio comparable to the software algorithm, using weights stored in a multi-cell consisting of four MTJs or more. Moreover, the presented solution has better energy efficiency in terms of energy consumed per single image processing, as compared to a similar design.

Superoxide dismutase and glutathione peroxidase activity in pregnancy complicated by diabetes.

The objective of the study was determination of the activity of superoxide dismutase (SOD) and glutathione peroxidase (GPx) in blood and placental tissues of pregnant women with pregnancy complicated by diabetes, pregnant women with physiological pregnancy, and non-pregnant women, as well as a comparative analysis of blood and placental tissue parameters in the groups of women examined. The material for the study was blood and placental tissue from 50 pregnant women who received treatment due to insulin-dependent diabetes (PD). For the control group, 50 pregnant women without diabetes (HP), and 30 non-pregnant women (NP) were selected. SOD activity in erythrocytes was evaluated by the method of spectrophotometry with the use of RANSOD kit (RANDOX Laboratories Ltd., UK). The activity of GPx activity in erythrocytes was determined according to the method by Paglia and Valentine using RANSEL kit (RANDOX Laboratories Ltd). The results were subject to statistical analysis. Insulin-dependent diabetes in pregnancy affects the activity of anti-oxidative enzymes. In the blood of women with pregnancy complicated by diabetes, the activity of anti-oxidative enzymes - SOD and GPx is higher than in the blood of women with physiological pregnancy and the control group. In the placental tissue from pregnancy complicated by diabetes, the activity of SOD significantly decreases, while the activity of GPx increases, compared to women in physiological pregnancy.