Brute Force: Agent Orang-utan

Accompanying any new Bond film is a cornucopia of branding; from watch sponsorships to cars and mobile phones. Bond is seen modelling sharp suits and designer shades. But there is another kind of agent modelling that has become increasingly popular in recent times due to available computing resources and the preference for our friend brute force.

Agent-based modelling is not something to do with 007. It’s an approach that enables what is called parallelisation, another drinking buddy to brute force.

The idea is to split-up the work-load into neat packets of autonomous tasks. Then divvy-up the task between the available resources and let them each just get on with it. Each worker or “agent” is assigned certain behaviours like always go left say, and, like a worker bee or ant, they knuckle down to the task in hand without worrying what everyone else is up to.

Because agents aren’t very social-types they can do their particular job at the same time as other agents, hence in parallel. At certain times they may report back to base with an update of how they’re doing or what they found-out. This could be when something happens or at a set time agreed with HQ.

Agents get their head down. If you give then a job to do they’ll carry-on doing it happily for however long you like, just don’t make it too complicated.

For example, if you wanted to find something you’d lost, car keys say, then you could set a team of agents on to the task of finding it. They’ll beaver away looking for it, maybe searching a small area each or randomly zig-zagging about the place. The trade-off may be between quantity and quality. Imagine you only had a set amount of cash to pay the search team with. If you were to have one, expensive guy hunting then he may move quicker than any cheap labour individual agent and be more skilled but there’s still only one of him. A separate agent could be a computer or one of the processors on a computer.

Splitting-up the work is not always such a simple thing to do though. Not everything can be parallelised and sometimes the effort of getting things into a fit shape so that it can be is just not worth it. In the lost car keys example it’s obvious how to share the task around, in space. But for other problems it’s not so straightforward. Imagine a task that each step was reliant on the previous, like on a production line, say making a car. Things could be made in parallel but when it comes to putting the car together certain things have to go in first and others later, like say, the steering column before the steering wheel. These things must therefore be done in serial, i.e. one after the other. Even in the searching problem it may be that the agents don’t find anything at first then they all meet-up and have a chat and decide to change how they’re going to search as a group, like focus more on one area over another. Each of these get-togethers would be serial events.

Agent-based systems can be relatively little hassle because once they’ve been set on their merry little way they can be left unsupervised to get on with it. The downside to this is that they’ll only act in the way that you’ve told to them to, which often means in a simple and loner way- A bit like a Goth high school drop-out. 

Brute Force: simulation

Simulation has got a pretty negative “rep” in recent years. It has come to be associated with faking it, inauthenticity and downright cheating. Simulation in sport is to feint injury or a foul in order to get an advantage or disadvantage the opposition. Players regularly throw themselves to the floor on a football pitch, arms out-stretched simulating a heinous foul so they can get a free kick or penalty or to get the other player booked or sent-off. Calling this simulation, rather than, say, cheating, is a relatively recent thing. Some football cultures see this drama as being clever, having the skill to convince the referee to be swayed in your favour. But this view point is in the minority, especially in the UK, and for a player to practice simulation is to be a bad boy.

Another use of simulation could be said when a participant is not being enough of a bad boy. By this I’m referring to the When Harry Met Sally sort of simulation. That is, simulation by the fairer sex in the act of love-making; hair swishing, table thumping faking. This particular form of simulation is also bad news, especially if your mates hear about it.

But it is not true that all simulation involves making a scene in one form or another. Faking it can be a good thing, and no-one’s feeling should get hurt in the process.

Simulation in a general sense is to make pretend and human beings do simulation every day, innumerable times. Simulation is what we do in our heads when we imagine something that isn’t real. Usually this is thinking of a fictional future to see what happens. These simulations take split seconds and often we’re not even aware of it. Simulation can be fun- imagining we win the lottery then what would we do with the money- to preventing serous peril- crossing the road in heavy traffic. Simulation in this form is called prediction and is how we can make half decent decisions. Prediction also happens when we want to approach a beautiful woman on the other side of the room. Our eyes meet hers and then “boom”, the minds races with chat-up lines and openers. We imagine what the response might be, the worst case scenario of a glass of wine in the face to the best- a wedding, kids, retirement on the beach.

Stats Apps

I was reading recently about projects which "gamify" your PhD. That means they take a PhD topic and make it into a computer game. The idea is this is a way to engage with the public, part of science communication. The FameLab and I'm a Scientistic Get Me Out Of Here scheme are other ways to get people interested by pitching PhDs in fun and simple terms.
In a similar vein to making computer games out of PhD projects I thought I'd see what apps there are out there around statistics. I have an Android phone so looked on the Google Play site. What I found was rather a lot, more than I expected at least. Generally they are simple tools for recording and dispaying simple summaries and graphs of small data samples. The user enters in the data by hand and then can choose things like descriptive statistics or histograms and regressions.
The other sort of app is the explanation tool. This is really a condensed version of Wikipedia.

I thought I'd try and come-up with some of my own ideas for stats apps:

• something to do with public health/cardiovascular disease/lifestyle risk factors. Maybe a calculator that takes how much excercies, diet and weight and gives the risks of things

• something that uses census data and makes it specific to you (where you live, age groups,...)

 [UPDATE 5/1/13 just found this which looks like a slick Beta version of what I had in mind!]

• something like a rumour/infection app. you can only get it by blue-tooth with another mobile (after the intial population has been set-up). so the idea is to gather data as part of an experiment to see how people interact and the spread of a "rumour"

• then it returns interesting statistics to the mobile app like what number in the chain you are, how long after initial infection (speed), network diagrams of infected with phone names labels (degrees of separation)
• the infection rate and recovery rate could be effected by imposing a time limit on how long the phone is infectious (can transmit app), prizes and incentives to passing on the app (e.g. every 100 people theres a prize draw for an iPad)...
• practically, there could be 2 big buttons on the phones home screen: one if the infected person tries to pass it on i.e. mentions it their friend and another to send it
•  in a time of bird flu, swine flu, etc this could be useful information about how people interact. it could also show how word-of-mouth or gossip works- often considered the best form of advertising.