Posts Tagged ‘Prediction’

Posted: July 29, 2012 by Wildcat in Uncategorized
Tags: , , , ,

If you’ve been walking around a public place lately, you’ve come in contact with a lot of people. Some of those people may have been sick. And if you’ve been hanging around enough of them as they cough and sneeze, then you might be about to get sick too. That may sound obvious, but Adam Sadilek at the University of Rochester in New York and colleagues have applied the idea to a pile of Twitter data from people in New York City, and found that they can predict when an individual person will come down with the flu up to eight days before they show symptoms. It’s a similar idea to Google Flu Trends, which tracks how often people search for “flu” and related terms on the search engine and uses that information to provide daily updates on where outbreaks are occurring and how they’re spreading. To see whether it was possible to bring such a service down to the level of the individual, Sadilek and his team analysed 4.4 million tweets tagged with GPS location data from over 630,000 users in the New York City area over one month in 2010. They trained a machine-learning algorithm to tell the difference between tweets by healthy people – who might say something like “I am so sick of this traffic!” – and someone who is actually sick and showing signs of the flu. The video above shows a heat map of flu occurrence over the course of one day, based on their findings. The researchers were able to predict when healthy people were about to fall ill – and then tweet about it – with about 90 per cent accuracy out to eight days in the future. (via One Per Cent: AI predicts when you’re about to get sick)

Posted: July 9, 2012 by Wildcat in Uncategorized
Tags: , , ,

A new tool automatically helps forecast emerging technologies, thanks to an innovative data-mining technique. Developed by Péter Érdi at the Hungarian Academy of Sciences in Budapest and colleagues, it works by analyzing the frequency with which prior-art (previous patents) are cited by other patents. Plotting how the frequency of these citations changes over time shows that patents can be grouped into related clusters. These clusters evolve, sometimes branching into new disciplines, sometimes merging with one another. Érdi’s team has written software that charts this evolution and helps predict whether existing technological fields can combine or diverge to create new areas of innovation. (via Patent trawler aims to predict next hot technologies | KurzweilAI)

Posted: May 17, 2012 by Wildcat in Uncategorized
Tags: , , ,

One hundred years from now, the role of science and technology will be about becoming part of nature rather than trying to control it. So much of science and technology has been about pursuing efficiency, scale and “exponential growth” at the expense of our environment and our resources. We have rewarded those who invent technologies that control our triumph over nature in some way. This is clearly not sustainable. We must understand that we live in a complex system where everything is interrelated and interdependent and that everything we design impacts a larger system. My dream is that 100 years from now, we will be learning from nature, integrating with nature and using science and technology to bring nature into our lives to make human beings and our artifacts not only zero impact but a positive impact to the natural system that we live in.

Joi Ito’s Near-Perfect Explanation of the Next 100 Years – Technology Review

Posted: April 12, 2012 by Wildcat in Uncategorized
Tags: , ,

The discovery, using state-of-the-art informatics tools, increases the likelihood that it will be possible to predict much of the fundamental structure and function of the brain without having to measure every aspect of it. That in turn makes the Holy Grail of modelling the brain in silico—the goal of the proposed Human Brain Project—a more realistic, less Herculean, prospect. “It is the door that opens to a world of predictive biology,” says Henry Markram, the senior author on the study, which is published this week in PLoS ONE. Within a cortical column, the basic processing unit of the mammalian brain, there are roughly 300 different neuronal types. These types are defined both by their anatomical structure and by their electrical properties, and their electrical properties are in turn defined by the combination of ion channels they present—the tiny pores in their cell membranes through which electrical current passes, which make communication between neurons possible.

Data mining opens the door to predictive neuroscience | Science Codex

I have come across a web sight presenting a novel concept of Artificial Intuition. Though preliminary, it seems to make a lot of sense. A theory-less predictive method might prove to be a significant as complementing theory and logic based methods. The author is Monica Anderson,

Here are a few highlights from the site:

Artificial Intuition is a new, different, and promising (but so far unproven) way to approach a large subset of the problems we believe require “Artificial Intelligence”.

Here I introduce the approach in general terms, but please note that the theory leads to a very specific, novel, and quite simple algorithm. Exploration of implementations is underway.

The purpose of Intelligence is Prediction. Evolution of the ability to predict agents and phenomena in the environment improved survival rates and created a strong evolutionary pressure to develop better and longer term predictions. This is the reason Intelligence evolved.

I define a “Bizarre Domain” as a problem domain that has all of these four properties: It is Chaotic, it requires a Holistic Stance, it contains Ambiguity, and it exhibits Emergent Properties. I examine sixteen kinds of problems that fall into these four categories. Each problem-kind poses serious problems for logic-based attempts to model the domain and solve problems in it. “Modeling the World”, and “Discovery of Semantics” are problems in Bizarre Domains.

Bizarre Systems

Bizarre Systems

Most humans have not been taught logical thinking, but most humans are still intelligent. Contrary to the majority view, it is implausible that the brain should be based on Logic; I believe intelligence emerges from millions of nested micro-intuitions, and that Artificial Intelligence requires Artificial Intuition. Intuition is surprisingly easy to implement in computers.

Certain situations are complex enough that predictions cannot be made to sufficient precision or sufficiently far ahead to be useful. We call this the region of the absurd; Logical models can not be made, and Intuition will not work either. But “close to the axes” we can use either Logic, Intuition, or either, depending on the problem and the requirements. A diagram is used to illustrate the point.

Complexity Versus Predictability

Intuition, which is what we use to handle our daily problems, can handle significantly more complex problems than science but is incapable of long-term predictions even for simple problems.

Higher up and close to the to the Y axis, Intuition based methods outperform Logic and Science. This is the area where we find Bizarre systems and Bizarre problem domains. Here we find the Discovery of Semantics of all kinds, such as understanding language, analyzing visual data and understand what we see, hearing melodies and sounds, and being able to make sense of the world in general. This is the area in which humans will outperform computers on most tasks. This is the domain of problems requiring Intelligence.

Areas of Competence

Areas of Competence

We can trade the Seven Values of Logic Based Science for about a dozen Benefits of Intuition Based Methods. The brain needs none of the former and provides all of the latter, which indicates that Artificial Intuition is a Biologically Plausible theory. The system is designed to encourage all of these at low levels. The most important features are expected to be emergent at higher levels.

The author does not mention subjects such as fuzzy logic and Bayesian networks that might be relevant to a theory-less prediction paradigm.  Much more can be found in the web site. A very interesting read.