evolving neural networks

[Roger Critchlow-2]

http://rspb.royalsocietypublishing.org/content/early/2012/04/04/rspb.2012.0206 has made quite a splash in the news. 

The high levels of intelligence seen in humans, other primates, certain cetaceans and birds remain a major puzzle for evolutionary biologists, anthropologists and psychologists. It has long been held that social interactions provide the selection pressures necessary for the evolution of advanced cognitive abilities (the ‘social intelligence hypothesis’), and in recent years decision-making in the context of cooperative social interactions has been conjectured to be of particular importance. Here we use an artificial neural network model to show that selection for efficient decision-making in cooperative dilemmas can give rise to selection pressures for greater cognitive abilities, and that intelligent strategies can themselves select for greater intelligence, leading to a Machiavellian arms race. Our results provide mechanistic support for the social intelligence hypothesis, highlight the potential importance of cooperative behaviour in the evolution of intelligence and may help us to explain the distribution of cooperation with intelligence across taxa.

The paper is open access.  

They evolve a population of neural networks that play the Prisoners' Dilemma or the Snowdrift Game amongst themselves, with fitness computed as the payoffs in the game rounds minus the size of your own neural network.  With the result that the neural networks _can_ evolve to become larger over time, the populations _can_ acquire a diversity in strategies that becomes a selection pressure for increasingly clever strategies for playing the games.

-- rec --

============================================================
FRIAM Applied Complexity Group listserv
Meets Fridays 9a-11:30 at cafe at St. John's College
lectures, archives, unsubscribe, maps at http://www.friam.org

[Carl Tollander]

As it might, in, um, the immune system?

On 4/11/12 4:59 PM, Roger Critchlow wrote:
> With the result that the neural networks _can_ evolve to become larger
> over time, the populations _can_ acquire a diversity in strategies
> that becomes a selection pressure for increasingly clever strategies
> for playing the games.

============================================================
FRIAM Applied Complexity Group listserv
Meets Fridays 9a-11:30 at cafe at St. John's College
lectures, archives, unsubscribe, maps at http://www.friam.org

[Merle Lefkoff]

Thank you, Roger.  I like this.  Merle

On Apr 11, 2012, at 4:59 PM, Roger Critchlow wrote:

http://rspb.royalsocietypublishing.org/content/early/2012/04/04/rspb.2012.0206 has made quite a splash in the news. 

The high levels of intelligence seen in humans, other primates, certain cetaceans and birds remain a major puzzle for evolutionary biologists, anthropologists and psychologists. It has long been held that social interactions provide the selection pressures necessary for the evolution of advanced cognitive abilities (the ‘social intelligence hypothesis’), and in recent years decision-making in the context of cooperative social interactions has been conjectured to be of particular importance. Here we use an artificial neural network model to show that selection for efficient decision-making in cooperative dilemmas can give rise to selection pressures for greater cognitive abilities, and that intelligent strategies can themselves select for greater intelligence, leading to a Machiavellian arms race. Our results provide mechanistic support for the social intelligence hypothesis, highlight the potential importance of cooperative behaviour in the evolution of intelligence and may help us to explain the distribution of cooperation with intelligence across taxa.

The paper is open access.  

They evolve a population of neural networks that play the Prisoners' Dilemma or the Snowdrift Game amongst themselves, with fitness computed as the payoffs in the game rounds minus the size of your own neural network.  With the result that the neural networks _can_ evolve to become larger over time, the populations _can_ acquire a diversity in strategies that becomes a selection pressure for increasingly clever strategies for playing the games.

-- rec --

============================================================
FRIAM Applied Complexity Group listserv
Meets Fridays 9a-11:30 at cafe at St. John's College
lectures, archives, unsubscribe, maps at http://www.friam.org

============================================================
FRIAM Applied Complexity Group listserv
Meets Fridays 9a-11:30 at cafe at St. John's College
lectures, archives, unsubscribe, maps at http://www.friam.org