An interesting corollory
on
Of Ants and Robots
·
· Score: 5, Interesting
This has been around in conventional AI for a while. There exists an optimization technique, which goes by the name of Ant Colony Systems (ACS) http://www.geocities.com/fastiland/Teaching/acs/sw arm.html. This technique uses the observed intuition that ants are often able to find the most optimal path between a food source and the nest without any global all knowing power telling them what it is. The way they do it is by leaving a trail of chemicals (Pheromones) whose odor persists for a while. A lot of ants play it safe and use the trail with the highest pheromone scent, however there are a few rebels who strike out a new path and few which prefer to take paths with lower pheromone concentrations. Thus with the expense of very few ants (agents) the colony as a whole is able to map out the most interesting parts of the state space with a loss of very few individuals and often able to get the most optimal paths. Needless to say this approach works best in bounded state spaces.
Just wanted to point out how stupid behavior and non-conformism at an individual level can often lead to a vibrant and healthy group and how it has been known to and exploited by computer scientists riding the Moore's law wave.....
The system described here is not your average random number generator with a text line output that any high-school kid can write.
Let us look at the system as it is designed to perform. If you were the system you would be put into a room with some objects. Only thing that you will know are things of interest. 'Paper with rock drawn on it is important', 'Paper with.......' and so on. You would also know when somebody shouts 'I WON' its a good thing for them. Essentially it has in its knowledge base a tiny number of features which somebody else has guaranteed to be of significance to its task.
The first challenge in building such a system is sensor fusion: i.e fusing the available audio and visual data to detect a state or an event of interest (I use the word event in the same sense as a trigger, something that prompts the change in state). The next and the biggest challenge is building the model of the game. Please check out http://www.doc.ic.ac.uk/~shm/ilp.html, for a better description of Inductive logic programming.
Seriously; the neatest thing about CogVis is not its ability to play Rock, Paper and Scissors, but its ability to actually go into an environment it has very little knowledge of and then observe, deduce and , not a blackbox model, as in say Neural Networks, but a human understandable model in first order logic
Slashdot Mirror
This has been around in conventional AI for a while. There exists an optimization technique, which goes by the name of Ant Colony Systems (ACS) http://www.geocities.com/fastiland/Teaching/acs/sw arm.html. This technique uses the observed intuition that ants are often able to find the most optimal path between a food source and the nest without any global all knowing power telling them what it is. The way they do it is by leaving a trail of chemicals (Pheromones) whose odor persists for a while. A lot of ants play it safe and use the trail with the highest pheromone scent, however there are a few rebels who strike out a new path and few which prefer to take paths with lower pheromone concentrations. Thus with the expense of very few ants (agents) the colony as a whole is able to map out the most interesting parts of the state space with a loss of very few individuals and often able to get the most optimal paths. Needless to say this approach works best in bounded state spaces.
Just wanted to point out how stupid behavior and non-conformism at an individual level can often lead to a vibrant and healthy group and how it has been known to and exploited by computer scientists riding the Moore's law wave.....
Think!!!
C'mon ppl get real
The system described here is not your average random number generator with a text line output that any high-school kid can write. Let us look at the system as it is designed to perform. If you were the system you would be put into a room with some objects. Only thing that you will know are things of interest. 'Paper with rock drawn on it is important', 'Paper with .......' and so on. You would also know when somebody shouts 'I WON' its a good thing for them. Essentially it has in its knowledge base a tiny number of features which somebody else has guaranteed to be of significance to its task.
The first challenge in building such a system is sensor fusion: i.e fusing the available audio and visual data to detect a state or an event of interest (I use the word event in the same sense as a trigger, something that prompts the change in state). The next and the biggest challenge is building the model of the game. Please check out http://www.doc.ic.ac.uk/~shm/ilp.html, for a better description of Inductive logic programming.
Seriously; the neatest thing about CogVis is not its ability to play Rock, Paper and Scissors, but its ability to actually go into an environment it has very little knowledge of and then observe, deduce and , not a blackbox model, as in say Neural Networks, but a human understandable model in first order logic