Blog: Cooperating Mini-Brains Show How Intelligence Evolved

Cooperating Mini-Brains Show How Intelligence Evolved
Live Science (04/10/12) Stephanie Pappas

Trinity College Dublin researchers recently developed computer simulation experiments to determine how human brains evolved intelligence. The researchers created artificial neural networks to serve as mini-brains. The networks were given challenging cooperative tasks and the brains were forced to work together, evolving the virtual equivalent of increased brainpower over generations. "It is the transition to a cooperative group that can lead to maximum selection for intelligence," says Trinity's Luke McNally. The neural networks were programmed to evolve, producing random mutations that can introduce extra nodes into the network. The researchers assigned two games for the networks to play, one that tests how temptation can affect group goals, and one that tests how teamwork can benefit the group. The researchers then created 10 experiments in which 50,000 generations of neural networks played the games. Intelligence was measured by the number of nodes added in each network as the players evolved over time. The researchers found that the networks evolved strategies similar to those seen when humans play the games with other humans. "What this indicates is that in species ancestral to humans, it could have been the transition to more cooperative societies that drove the evolution of our brains," McNally says.

View Full Article

Blog: A New System Increases the Reliability of Opinion Polls

A New System Increases the Reliability of Opinion Polls
Universidad Politecnica de Madrid (Spain) (04/26/11) Eduardo Martinez

Universidad Politecnica de Madrid researchers have developed a fuzzy neural network that uses a numerical and categorical imputation method to reconstruct incomplete data sets, which could be used to determine the voting intention of a voter that has not answered all the opinion poll questions with near 90 percent accuracy. The system, developed by Jesus Cardenosa and Pilar Rey del Castillo, also can be used for medical diagnosis or surveying using categorical variables. The system works by first defining the distances between categories using fuzzy logic. It then determines where each category is located within the different dataset spaces using the neural network. Finally, the system extends the network architecture to all the data and processes the missing data.

View Full Article

Blog: Fuzzy Thinking Could Spot Heart Disease Risk

Fuzzy Thinking Could Spot Heart Disease Risk
ScienceDaily (09/16/10)

Anna University's Khanna Nehemiah and colleagues have used fuzzy logic, a neural network computer program, and genetic algorithms to create a medical diagnostic system for predicting the risk of cardiovascular disease in patients. They employed fuzzy logic to teach a neural network to examine patient data and identify correlations that would indicate a person's risk factor. The medical diagnostic system has produced a statistical model that improves on previous efforts and is accurate 90 percent of the time in determining patient risk, according to the researchers. "A clinical-decision support system should consider issues like representation of medical knowledge, decision making in the presence of uncertainty and imprecision, choice and adaptation of a suitable model," according to the researchers. They say the new model addresses all of these points. The fuzzy neural network could be further enhanced by modifying its architecture, and by extracting generic rules to find a more precise risk factor.

View Full Article

Blog: Neurons to Power Future Computers

Neurons to Power Future Computers
BBC News (07/23/10)

University of Plymouth computer scientists led by Thomas Wennekers are developing novel computers that mimic the way neurons are built and how they communicate. Neural-based computers could lead to improvements in visual and audio processing. "We want to learn from biology to build future computers," Wennekers says. "The brain is much more complex than the neural networks that have been implemented so far." The researchers are collecting data about neurons and how they are connected in one part of the brain. The project is focusing on the laminar microcircuitry of the neocortex, which is involved in higher brain functions such as seeing and hearing. Meanwhile, Manchester University professor Steve Furber is using the neural blueprint to produce new hardware. Furber's project, called Spinnaker, is developing a computer optimized to run like biology does. Spinnaker aims to develop innovative computer processing systems and insights into the way that several computational elements can be connected. "The primary objective is just to understand what's happening in the biology," Furber says. "Our understanding of processing in the brain is extremely thin."

View Full Article