(a): Scheme of the double-layer perceptron; Experimental data. (b): Output signal within the epochs before (left) and after (right) training and expected output signal (dotted). (c): Synaptic weights and (d): corresponding feature plane partition (area above and below the plane y = 4,5 is the class “1” and “0”, correspondingly). Obtained separating planes are implemented by corresponding neurons in the first layer [169]. Reprinted from A.V. Emelyanov, D.A. Lapkin, V.A. Demin, V.V. Erokhin, S. Battistoni, G. Baldi, A. Dimonte, A.N. Korovin, S. Iannotta, P.K. Kashkarov, and M.V. Kovalchuk, “First step towards the realization of a double layer perceptron, based on organic memristive decices”, AIP Adv., 6, 111301 (2016) with the permission of AIP Publishing.