Beauty is in the efficient coding of the beholder

Abstract

Sexual ornaments are often assumed to be indicators of mate quality. Yet it remains poorly known how certain ornaments are chosen before any coevolutionary race makes them indicative. Perceptual biases have been proposed to play this role, but known biases are mostly restricted to a specific taxon, which precludes evaluating their general importance in sexual selection. Here we identify a potentially universal perceptual bias in mate choice. We used an algorithm that models the sparseness of the activity of simple cells in the primary visual cortex (or V1) of humans when coding images of female faces. Sparseness was found positively correlated with attractiveness as rated by men and explained up to 17% of variance in attractiveness. Because V1 is adapted to process signals from natural scenes, in general, not faces specifically, our results indicate that attractiveness for female faces is influenced by a visual bias. Sparseness and more generally efficient neural coding are ubiquitous, occurring in various animals and sensory modalities, suggesting that the influence of efficient coding on mate choice can be widespread in animals.

Keywords: aesthetics; face; sensory bias; sensory exploitation; sexual selection; sparse coding.

Figure 1.

Workflow for estimating the sparseness of face images. We first trained 144 basis functions Φ_i (of size 12×12) to reproduce natural scenes using the same sparseness algorithm and model parameters as in [9]. Then, for each face image we convolved basis functions with n patches p(x,y) and worked out the combination of activity coefficients a_i (i.e. the weights of Φ_i) that minimizes a cost function. Coordinates (x,y) of patch centres take all possible values along the width and the height of an image, respectively. The cost function accounts for both the quality of face reconstruction and the sparseness of a_i distribution. λ determines the relative importance of these two components. The quality of reconstruction is given by the error mean square. During minimization, sparseness of a_i was estimated by summing each coefficient activity (scaled by constant σ) passed through a nonlinear function S (see [8]). Here, λ=0.044 and σ=0.316. Analyses were repeated with 64 basis functions (8×8), and with 256 basis functions (16×16). We calculated two measures of sparseness for each face: the kurtosis of a_i distribution and the activity ratio (using |ai|). A sparse representation of face has high kurtosis and low activity ratio.

Figure 2.

Correlation between attractiveness and kurtosis of a_i distribution in dataset 1. Attractiveness is an average score within the interval [0; 100]. The number of basis functions and the size of receptive fields were set to 16×16.