![a neural network that looks like a human brain - Generated with AI](https://i0.wp.com/fullsteamahead365.com/wp-content/uploads/2024/07/a-neural-network-that-looks-like-a-human-brain-01.jpeg?fit=1024%2C1024&ssl=1)
Traditional neural networks don't work like the human brain.
In a paper in the journal Nature Human Behaviour, “The Neural Network RTNet Exhibits the Signatures of Human Perceptual Decision-Making,” a team from the Georgia Tech School of Psychology shows that while convolutional neural networks show promise as models of biological vision, they have limited applicability to human decision-making. Instead, the team has developed a new neural network, RTNet, that generates stochastic decisions and human-like response time (RT) distributions. Comprehensive tests showed RTNet reproduces all foundational features of human accuracy, RT, and confidence, and does so better than all current alternatives. The abstract follows.
![a neural network that looks like a human brain - Generated with AI](https://i0.wp.com/fullsteamahead365.com/wp-content/uploads/2024/07/a-neural-network-that-looks-like-a-human-brain-02.jpeg?resize=640%2C640&ssl=1)
Abstract
Convolutional neural networks show promise as models of biological vision. However, their decision behaviour, including the facts that they are deterministic and use equal numbers of computations for easy and difficult stimuli, differs markedly from human decision-making, thus limiting their applicability as models of human perceptual behaviour. Here we develop a new neural network, RTNet, that generates stochastic decisions and human-like response time (RT) distributions. We further performed comprehensive tests that showed RTNet reproduces all foundational features of human accuracy, RT and confidence and does so better than all current alternatives. To test RTNet’s ability to predict human behaviour on novel images, we collected accuracy, RT and confidence data from 60 human participants performing a digit discrimination task. We found that the accuracy, RT and confidence produced by RTNet for individual novel images correlated with the same quantities produced by human participants. Critically, human participants who were more similar to the average human performance were also found to be closer to RTNet’s predictions, suggesting that RTNet successfully captured average human behaviour. Overall, RTNet is a promising model of human RTs that exhibits the critical signatures of perceptual decision-making.