Herself’s Artificial Intelligence

Several companies are working on intelligent agents to help you in your computer interactions, ( see Lua created assistant ) and here is yet another one, Magitti.

Magitti is different in that it is taking advantage of some of the phones unique advantages: portability, gps and that it travels with you all day.

It is also different in that there is a built in revenue stream. Magitti recommends local restaurants and shopping at appropriate times and locations.

There are few details to be found at PARC yet. More will be forthcoming I’m sure. There are papers available for a fee at IEEE search for ‘PARC and mobile’.

See also:

Agents, bots and spiders

Reasoning using graphical models is rapidly gaining popularity. Not just used in reasoning they are also becoming useful in computer vision where they are used to classify objects.

Graphical models include: constraint networks, Markov random fields, belief networks, Bayes networks and influence diagrams.

Traditionally algorithms for these networks have been either inference-based or search based. While inference algorithms are not practical time wise for most problems outside the classroom some of the search algorithms perform quite well. Combinations of these algorithms are being used to solve knowledge representation problems not otherwise practical with just inference based algorithms. Often algorithms are tailored for each specific problem.

The advantages of this method is that all possible outcomes are known and declared in the graphical model. Also the models are easily understood by humans, and the techniques used are well understood.

Nodes on the graph represent facts or states and may be known or unknown, hidden or visible.

Connections between nodes may be hidden or not, they may be probabilities or equations and represent connections between the data.

The graphical representation allows us to decompose the big problem into smaller simpler to solve problems.

More information:
Graphical Model Algorithms at UC Irvine has a large list of software and example problems using graphical models in knowledge reasoning.
There are some Power Point and PDF tutorials you can download from Microsoft
Video lecture on Graphical models
A list of links to several software tools for doing graphical models
Graphical knowledge representation for human detection ( pdf )
Mean Field Theory for Graphical Models
Graphical Models for Discovering Knowledge (excellent beginner’s paper )

See also:
Bayesian logic
Knowledge representation and predicate calculus
Hidden Markov models

Forgotten and mislaid passwords could be a thing of the past. A German start-up claims its typing recognition system will solve the problems associated with traditional password authentication.The Regensburg-based company said that its system is based on recognising individuals typing habits including speed, rhythm, agility, corrective behaviour and use of shift keys. Using a neural network the system is said to be keyboard independent and can adapt to changes in typing behaviour. To access a PC or web application users must type a single sentence. Psylock said that, unlike passwords, typing behaviours could not be stolen or copied. [ read more German entrepreneurs claim to solve the password problem]

More information:
Psylock
A machine learning approach to keystroke dynamics and authentication

Truth is I already feel like Jane somedays. I push buttons on the dishwasher, washer, dryer, roomba, scooba and now if I just had Rosie to water the plants and put the clean dishes and clothes away life could be good.

A personal robot that can water plants, remind owners to take their medication, turn lights on and off, and control appliances has won a contest sponsored by iRobot.

Danh Trinh, 35, of Towson, Md., won iRobot’s Create Challenge contest and its $5,000 prize, with his Personal Home Robot, the company announced Tuesday.

iRobot Create is a preassembled programmable robot designed so developers can create new robots without having to build everything from scratch. . . . [ read more Personal Robot Wins iRobot's Create Challenge]

More information:
Picture of the robot
Tom’s Hardware iRobot Create Challenge

Can a fringe branch of mathematics forecast the future? A special adviser to the CIA, Fortune 500 companies, and the U.S. Department of Defense certainly thinks so. If you listen to Bruce Bueno de Mesquita, and a lot of people don’t, he’ll claim that mathematics can tell you the future. In fact, the professor says that a computer model he built and has perfected over the last 25 years can predict the outcome of virtually any international conflict, provided the basic input is accurate. What’s more, his predictions are alarmingly specific. His fans include at least one current presidential hopeful, a gaggle of Fortune 500 companies, the CIA, and the Department of Defense. Naturally, there is also no shortage of people less fond of his work. “Some people think Bruce is the most brilliant foreign policy analyst there is,” says one colleague. “Others think he’s a quack.” . . .[ read more Good Magazine - The New Nostradamus ]

Unfortunately none of B de Mesquita’s papers were readily available. You can access several from J Stor if your school or local library has access. So I can’t verify if his predictions do in fact come true. He uses game theory, math and computer simulations to predict political outcomes. Game theory has had quite a bit of success in political predictions so it is entirely possible he has been very successful. According to B de Mesquita 90% of them have come to pass.

More information:
Math Trek: Mathematical Fortune Telling
NYU Faculty – Bruce Bueno De Mesquita

I did find several articles published in political magazines.
How foreign aid can help the poor and why it doesn’t by Bruce Bueno de Mesquita ( National Review )
The political roots of poverty: The economic logic of autocracy (National Interest )
Political Instability as a Source of Growth ( Business Wire )

See also:
Game Theory