That is, they succeeded in simulating the principles of human social intelligence, which opened new horizons for research.
Researchers trained a neural network to predict player responses in a game that simulates the classic Prisoner’s Dilemma. A modification of “fun” was used during the experiment.
The three modules of the latest AI model work together to analyze human behavior. The first module is based on the principle of “reverse planning” and can draw conclusions about a person’s preferences and beliefs.
The second module compares the outcome of the game with the expectations of each participant. The third then predicts the emotions that the participants might have depending on the outcome and expectations of the game.
When testing the model based on data not used during training, it was found that the neural network copes with the task of predicting emotions better than any known model.
The main advantage of innovation lies in its ability to mimic human reasoning and create predictions based on expectations and known data about humans.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
