Herself’s Artificial Intelligence

Most datamining is either done using private corporate databases, online government databases, or with web bots, spiders and scrapers. RSS has made data mining the web trivial with PERL. I’m told it is trival with PHP also, I’m still experimenting with that.

Currently, with the help of computers, most fields of science, the government and businesses are collecting data faster than they can comb through it. Some agencies have what would be hundreds of years worth of data if it had to be parsed by humans. So we need to use artificially intelligent datamining to sort the data, develop useful informative rules about the data, and or put it into useful formats for us humans.

This task of artificial intelligence is often put under the category of ‘machine learning’. Sometimes a set of rules is used. The rules may be created by an expert ( domain knowledge ) or discovered through machine learning using statistics.

Problems with this type of machine learning include coming up with an insane number of rules that are far too specific ( over fitting ) and using example data that skews the learning. Other problems include when do you decide you have the best set of rules? At what point is your algorithm good enough? Do you want all possible out comes or is it only specific outcomes you need? An example would be do you need 40 categories of healthy plant or only descriptions and diseases for unhealthy ones?

Datamining has four main styles of sorting through data. Classification: classes are presented and future data is to be sorted into one of the given classes. Association: associations between data are sought. Clustering: data is sorted into clusters usually using various traits as vectors. Prediction: in which some specific information, usually numeric is to be output.

Data details for data mining is often stored in ARFF Attribute-Relation File Format

More information:
Applications of Machine Learning and Rule Induction
Machine Learning ( Theory )
UT ML Group: Text Data Mining ( several papers here )
UCI Machine Learning Repository has over 160 data sets for you to use to test and develop your AI.

See also:
Electronic cop solves crimes
Finding new diseases for known cures

It is hard to argue with sending in robots instead of humans to a war zone. Lives get saved, the technology is oh so cool, but one has to wonder if we are not in fact beginning the creation our own terminator?

Unmanned “Surge”: 3000 More Robots for War
U.S. military robots ran 30,000 missions in 2006 — hunting for, and getting rid of, improvised explosives. Now, the military has launched a crash project to radically increase its unmanned ground forces. Call it the robotic equivalent of the “surge.”

Iraq’s Coming Robot Wars
With military recruitment a constant struggle, the U.S. Army is coming up with a new way to come up with bodies: it is going to build them. This week, the Army begins a “drive-off” to see what contractor is going to provide up to 1,000 bomb-clearing robots by year’s end, with a possible follow-on order for 2,000 more. The requirement is for a remote-controlled, wireless robot that weighs 50 pounds or less “to be used for Improvised Explosive Device (IED) detection and identification,” according to the Pentagon’s solicitation.

Army to deploy robots that shoot
Next year, the U.S. Army will give robots machine guns, although humans will firmly be in control of them.

The Army next March will begin to deploy Talon robots from Waltham, Mass.-based Foster-Miller. The robots will be mounted with M240 or M249 machine guns, said a Foster-Miller spokesman. The units also can be mounted with a rocket launcher. Defense agencies have been testing an armed version of the Talon since 2003.

Predator Soars To Record Number of Sorties
When terrorists tried shooting mortar rounds at Balad Air Base in July, they didn’t count on the tireless, unblinking eye of an MQ-1 Predator unmanned aerial vehicle overhead, transmitting their every move to airmen on the ground here. Airmen assigned to the 46th Expeditionary Reconnaissance Squadron here kept the Predator overhead July 24 watching the men while they confirmed what they were seeing with a joint terminal attack controller on the ground.

Urban Challenge
The DARPA Urban Challenge is an autonomous vehicle research and development program with the goal of developing technology that will keep warfighters off the battlefield and out of harm?s way. The Urban Challenge features autonomous ground vehicles maneuvering in a mock city environment, executing simulated military supply missions while merging into moving traffic, navigating traffic circles, negotiating busy intersections, and avoiding obstacles.

US Military turns to competition for robot “surge”
The US military has already upped the arsenal of its robots deployed in Iraq, and it now looks to be planning to expand its non-human forces even further, with it recently putting out word of a competition to find a company that can quickly deliver a slew of new bots. According to Wired’s Danger Room, these new robots won’t be armed, but will instead mainly be used for reconnaissance duty, and must include the ability to look inside car windows and peer underneath vehicles. Due to the urgent need for the bots, the Army’s done away with the usual formal bid process and will effectively be awarding a contract on the spot to the winner of the competition, who will be required to deliver its first bots within ten days.

See also:
What happens when weapons development goes private?

More information:
Non-answer on Armed Robots Pullout from Iraq Reveals Fragile Bot Industry
Wired Gallery – Inside the Navy’s Armed Robot Labs