Dreams, Neural Networks and Images of Thoughts: Towards a Comprehensive Theory of Visual Cognition

The article argues that our concepts are deeply rooted in the architecture of visual processing. The argument is based on evidence provided by two seemingly very distant theories of mind together with two sorts of corresponding visions: Freud’s theory of dreams, which suggests oneiric visions represent our thoughts and the mechanical model of the mind developed in the context of computer science. As will be argued, Freud’s findings are in fact supported by advances in this field, in particular by deep convolutional neural networks (DCNNs) which mirror the activity of visual cortex, producing visions strikingly similar to dreams. An in-depth analysis of such images, supported by insights from empiricism and conceptual metaphor theory, reveals that they represent visual universals, as well as more fragmentary notions pertaining to features, and complete abstractions, such as those found in language and in mathematics. This finding points towards a more comprehensive thesis about the links of vision to reflection: the crucial insight that will be developed and defended in this article is that the architecture of visual processing is the basis of the conceptual structures that underpin cognition.