“…Therefore, to study various dynamical behaviours of CNNs with proportional delays is of important theoretical and practical significants. But until now, there is only one published work dealing with the exponential stability of competitive neural networks with proportional delays. In , the authors discussed the exponential stability of CNNs with multi‐proportional delays of the form for t ≥ 1, i , j = 1,2,…, n , where x i ( t ) denotes the neuron current activity level; m i j is the synaptic efficiency; a i > 0 is the changing rate for neuron i ; b i j and c i j are constants which denote the strengths of connectivity between the cells j and i at time t and connection weights at time q j t respectively; d j is a given arbitrarily constant; q j is proportional delay factor and satisfies 0 < q j ≤ 1, q j t = t − (1 − q j ) t , in which (1 − q j ) t corresponds to the time delay function, and (1 − q j ) t → ∞ as q j ≠ 1, t → ∞ ; denotes the external input; B i > 0 is an external stimulus intensity; ε is a fast time scale decided by STM and ε > 0, f i (·) is the nonlinear activation function.…”