Artificial neural networks (ANNs) providing sophisticated, power-efficient classification are finding their way into thin-film electronics. Thin-film technologies require robust, layout-efficient devices with facile manufacturability. Here, we show how the multimodal transistor’s (MMT’s) transfer characteristic, with linear dependence in saturation, replicates the rectified linear unit (ReLU) activation function of convolutional ANNs (CNNs). Using MATLAB, we evaluate CNN performance using systematically distorted ReLU functions, then substitute measured and simulated MMT transfer characteristics as proxies for ReLU. High classification accuracy is maintained, despite large variations in geometrical and electrical parameters, as CNNs use the same activation functions for training and classification.

A novel compact realization of the XNOR/XOR function is demonstrated with multimodal transistors (MMTs). The multimodal thin-film transistors (MMT's) structure allows efficient use of layout area in an implementation optimized for unipolar thin-film transistor (TFT) technologies, which may serve as a multipurpose element for conventional and emerging large-area electronics. Microcrystalline silicon device fabrication is complemented by physical simulations.