Abstract
This article presents an analog multilayer perceptron (MLP) neural network circuit with on‐chip back propagation learning. This low power and small area analog MLP circuit is proposed to implement as a classifier in an electronic nose (E‐nose). Comparing with the E‐nose using microprocessor or FPGA as a classifier, the E‐nose applying analog circuit as a classifier can be faster and much smaller, demonstrate greater power efficiency and be capable of developing a portable E‐nose [1]. The system contains four inputs, four hidden neurons, and only one output neuron; this simple structure allows the circuit to have a smaller area and less power consumption. The circuit is fabricated using TSMC 0.18 μm 1P6M CMOS process with 1.8 V supply voltage. The area of this chip is 1.353×1.353 mm2 and the power consumption is 0.54 mW. Post‐layout simulations show that the proposed analog MLP circuit can be successively trained to identify three kinds of fruit odors.