A recurrent network model for the phase invariance of complex cell responses

Abstract Cortical amplification is a mechanism for modifying the selectivity of neurons through recurrent interactions. Although conventionally used to enhance selectivity, cortical amplification can also broaden it, de-tuning neurons. Here we show that the spatial-phase invariance of complex cell responses in primary visual cortex can arise using recurrent amplification of feedforward input. Neurons in the model network respond like simple cells when recurrent connections are weak and complex cells when they are strong. Simple or complex cells can coexist in such a network, and they can have a range of selectivities for image characteristics such as spatial frequency.