Neural Information Processing Systems http://nips.cc/

Understanding how humans perceive the likability of high-dimensional "objects"

Trust is the foundation of every area of life. Without it, it is difficult to build lasting relationships. Unfortunately, in recent years, trust has been severely damaged by the spread of fake news and disinformation, which has become a serious social problem. In addition to trust, the factor influencing interpersonal relationships is perceived attractiveness, which is currently created to a large extent by digital media. Understanding the principles of judging others can be helpful in fighting prejudice and rebuilding trust in society. One way to learn about people's choices is to record their brain activity as they make choices. The article presents an experiment in which the faces of different people were presented, and the participants' task was to assess how much they can trust a given person and how attractive they are. During the study, the EEG signal was recorded, which was used to build models of logistic regression classifiers. In addition, the most active areas of the brain that participate in the assessment of trust and attractiveness of the face were indicated.

If you're sick of being turned down by people who are'out of your league', a new online tool may finally get you the right match. Hot Chat 3000 is a bizarre online chatroom that uses AI to score your looks and connect you with someone of a similar'hotness' ranking. The chatroom is the creation of MSCHF, a US art collective based in New York that counts Wordle creator Josh Wardle among its staff members. According to MSCHF, attractiveness ratings are predicted by a large machine learning model that was trained by OpenAI, the company responsible for ChatGPT. It follows the new online game that makes you guess whether you're speaking to an AI bot or a fellow human.

This work presents a method for estimating human facial attractiveness, based on supervised learning techniques. Numerous facial features that describe facial geometry, color and texture, combined with an average human attractiveness score for each facial image, are used to train various predictors. Facial attractiveness ratings produced by the final predictor are found to be highly correlated with human ratings, markedly improving previous machine learning achievements. Simulated psychophysical experiments with virtually manipulated images reveal preferences in the machine's judgments which are remarkably similar to those of humans. These experiments shed new light on existing theories of facial attractiveness such as the averageness, smoothness and symmetry hypotheses.

One reason for the widespread interest in AI is that it has the potential to reduce the degree of bias underpinning human decisions. For example, meta-analytic studies have long highlighted the pervasive nature of bias in hiring and recruitment. Even in the rich and liberal world, there are many biases at play in the workplace, which account for the unmeritocratic or unfair advantage that some groups have over others, irrespective of their actual talent or potential: sexism, racism, and ageism, to name just a few. But one of the most prominent biases is hardly ever discussed or acknowledged, namely the beauty bias -- also known as "lookism." Indeed, the existence of a beauty premium in the labor market is well-documented.

Understanding how humans perceive the likability of high-dimensional ``objects'' such as faces is an important problem in both cognitive science and AI/ML. Existing models generally assume these preferences to be fixed. However, psychologists have found human assessment of facial attractiveness to be context-dependent. Specifically, the classical Beauty-in-Averageness (BiA) effect, whereby a blended face is judged to be more attractive than the originals, is significantly diminished or reversed when the original faces are recognizable, or when the blend is mixed-race/mixed-gender and the attractiveness judgment is preceded by a race/gender categorization, respectively. This "Ugliness-in-Averageness" (UiA) effect has previously been explained via a qualitative disfluency account, which posits that the negative affect associated with the difficult race or gender categorization is inadvertently interpreted by the brain as a dislike for the face itself. In contrast, we hypothesize that human preference for an object is increased when it incurs lower encoding cost, in particular when its perceived {\it statistical typicality} is high, in consonance with Barlow's seminal ``efficient coding hypothesis.'' This statistical coding cost account explains both BiA, where facial blends generally have higher likelihood than ``parent faces'', and UiA, when the preceding context or task restricts face representation to a task-relevant subset of features, thus redefining statistical typicality and encoding cost within that subspace. We use simulations to show that our model provides a parsimonious, statistically grounded, and quantitative account of both BiA and UiA. We validate our model using experimental data from a gender categorization task. We also propose a novel experiment, based on model predictions, that will be able to arbitrate between the disfluency account and our statistical coding cost account of attractiveness.

Understanding how humans perceive the likability of high-dimensional ``objects'' such as faces is an important problem in both cognitive science and AI/ML. Existing models generally assume these preferences to be fixed. However, psychologists have found human assessment of facial attractiveness to be context-dependent. Specifically, the classical Beauty-in-Averageness (BiA) effect, whereby a blended face is judged to be more attractive than the originals, is significantly diminished or reversed when the original faces are recognizable, or when the blend is mixed-race/mixed-gender and the attractiveness judgment is preceded by a race/gender categorization, respectively. This "Ugliness-in-Averageness" (UiA) effect has previously been explained via a qualitative disfluency account, which posits that the negative affect associated with the difficult race or gender categorization is inadvertently interpreted by the brain as a dislike for the face itself. In contrast, we hypothesize that human preference for an object is increased when it incurs lower encoding cost, in particular when its perceived {\it statistical typicality} is high, in consonance with Barlow's seminal ``efficient coding hypothesis.'' This statistical coding cost account explains both BiA, where facial blends generally have higher likelihood than ``parent faces'', and UiA, when the preceding context or task restricts face representation to a task-relevant subset of features, thus redefining statistical typicality and encoding cost within that subspace. We use simulations to show that our model provides a parsimonious, statistically grounded, and quantitative account of both BiA and UiA. We validate our model using experimental data from a gender categorization task. We also propose a novel experiment, based on model predictions, that will be able to arbitrate between the disfluency account and our statistical coding cost account of attractiveness.

This work presents a method for estimating human facial attractiveness, based on supervised learning techniques. Numerous facial features that describe facial geometry, color and texture, combined with an average human attractiveness score for each facial image, are used to train various predictors. Facial attractiveness ratings produced by the final predictor are found to be highly correlated with human ratings, markedly improving previous machine learning achievements. Simulated psychophysical experiments with virtually manipulated images reveal preferences in the machine's judgments which are remarkably similar to those of humans. These experiments shed new light on existing theories of facial attractiveness such as the averageness, smoothness and symmetry hypotheses. It is intriguing to find that a machine trained explicitly to capture an operational performance criteria such as attractiveness rating, implicitly captures basic human psychophysical biases characterizing the perception of facial attractiveness in general.

This work presents a method for estimating human facial attractiveness, based on supervised learning techniques. Numerous facial features that describe facial geometry, color and texture, combined with an average human attractiveness score for each facial image, are used to train various predictors. Facial attractiveness ratings produced by the final predictor are found to be highly correlated with human ratings, markedly improving previous machine learning achievements. Simulated psychophysical experiments with virtually manipulated images reveal preferences in the machine's judgments which are remarkably similar to those of humans. These experiments shed new light on existing theories of facial attractiveness such as the averageness, smoothness and symmetry hypotheses. It is intriguing to find that a machine trained explicitly to capture an operational performance criteria such as attractiveness rating, implicitly captures basic human psychophysical biases characterizing the perception of facial attractiveness in general.