Computer model can predict human behavior and learning

November 7, 2008

A computer model that can predict how people will complete a controlled task and how the knowledge needed to complete that task develops over time is the product of a group of researchers, led by a professor from Penn State's College of Information Sciences and Technology.

Frank Ritter, associate professor of IST and psychology, and his research associates, used the Soar programming language, which is designed to represent human knowledge, on a 20-trial circuit troubleshooting task most recently done by 10 students at the University of Nottingham, UK.

Each participant was to identify faults in a circuit system after memorizing the organization of its components and switches. This process was repeated 20 times for each person, with the series of tests chosen randomly each time. Their choices and reaction times were recorded and compared with the computer model's results.

Much like the students, the computer model, called Diag, learned as it went through each test and developed the knowledge for completing the task quickly and efficiently.

"The model does not merely accurately predict problem-solving time for the human participants; it also replicates the strategy that human participants use, and it learns at the same rate at which the participants learn," Ritter said.

In most cases, the model came within two to four seconds of predicting how long it would take each participant to solve the problem and it fit eight out of the 10 participants' problem-solving times very well. Ritter said the results outlined in the paper were consistent with previous trials, showing the development of regularity in the model.

"The project shows we can predict human learning on a fine-grained level," Ritter said. "Everyone thinks that's possible, but here's an actual model doing it. The model provides a detailed representation of how a transfer works, and that transfer process is really what education is about."

Ritter worked with Peter Bibby and two research assistants at the University of Nottingham. Their paper, "Modeling How, When, and What is Learned in a Simple Fault-Finding Task," appeared in the July/August 2008 issue of Cognitive Science.

Source: Penn State

Explore further: When AI is made by AI, results are impressive

Related Stories

When AI is made by AI, results are impressive

December 7, 2017
(Tech Xplore)—Researchers exploring AI systems are making news and familiarizing the public with terms like reinforcement learning and machine learning. Recent headlines are still making some heads turn in surprise. AI ...

Technique illuminates the inner workings of artificial-intelligence systems that process language

December 11, 2017
Neural networks, which learn to perform computational tasks by analyzing huge sets of training data, have been responsible for the most impressive recent advances in artificial intelligence, including speech-recognition and ...

How developing visual system axons stay in the correct layer

December 8, 2017
Scientists at Tokyo Tech have made an important discovery concerning the development of layer-specific axonal connections in the developing visual system of Drosophila flies. This discovery provides valuable insights into ...

Human-dog bond provides clue to treating social disorders

December 4, 2017
The chemistry behind social behaviour in animals, including the bond between people and dogs – and the lack of one between humans and wolves – could help scientists identify new ways of treating social disorders such ...

Scientists are studying the problem of modeling the cognitive dissonance phenomenon

November 17, 2017
Lobachevsky University (UNN) scientists Alexander Petukhov and Sofya Polevaya are studying the phenomenon of cognitive dissonance. They rely on the theory of information images and a mathematical model developed on the basis ...

The brain auditions different cells when learning a task, some don't make the cut

November 14, 2017
For decades, neuroscientists have wondered how the brain can continue to learn new skills without needing to grow in size or volume over a person's lifetime. Evidence suggests that the number of brain cells - such as neurons ...

Recommended for you

Suicidal thoughts rapidly reduced with ketamine, finds study

December 14, 2017
Ketamine was significantly more effective than a commonly used sedative in reducing suicidal thoughts in depressed patients, according to researchers at Columbia University Medical Center (CUMC). They also found that ketamine's ...

Do bullies have more sex?

December 14, 2017
Adolescents who are willing to exploit others for personal gain are more likely to bully and have sex than those who score higher on a measure of honesty and humility. This is according to a study in Springer's journal Evolutionary ...

Children's screen-time guidelines too restrictive, according to new research

December 14, 2017
Digital screen use is a staple of contemporary life for adults and children, whether they are browsing on laptops and smartphones, or watching TV. Paediatricians and scientists have long expressed concerns about the impact ...

Eating together as a family helps children feel better, physically and mentally

December 14, 2017
Children who routinely eat their meals together with their family are more likely to experience long-term physical and mental health benefits, a new Canadian study shows.

The iceberg model of self-harm

December 14, 2017
Researchers have created a model of self-harm that shows high levels of the problem in the community, especially in young girls, and the need for school-based prevention measures.

Anti-stress compound reduces obesity and diabetes

December 13, 2017
For the first time, scientists from the Max Planck Institute of Psychiatry in Munich could prove that a stress protein found in muscle has a diabetes promoting effect. This finding could pave the way to a completely new treatment ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.