## Wolfram Alpha

November 2, 2010 Leave a comment

** **

*Wolfram Alpha* is a “computational knowledge engine” developed by Stephen Wolfram for the purpose of finding definitive answers to questions and presenting them with maximum clarity. It is an online service that computes the answers to the questions submitted by the users in natural language by using a pre-structured database. Here “compute” word is used rather than “find” because this service doesn’t simply return documents that might contain the answers, like Google does, and it isn’t just a giant database of knowledge, like the Wikipedia. Instead, it understands and then computes answers to certain kinds of questions, like questions that have factual answers such as “What is the location of Timbuktu?” or “How many protons are in a hydrogen atom?” or “What was the average rainfall in Boston last year?“. It computes answers instead of just looking them up.

*Wolfram Alpha* was announced in March 2009 by Stephen Wolfram, and was released to the public on May 15, 2009.

*Wolfram Alpha* perhaps represents what may be a new approach to creating an “intelligent machine”. It’s simpler than top down artificial intelligence and easier than the original vision of Semantic Web. Its goal is to build on the achievements of science to provide a single source that can be relied on by everyone for definite answers to questions.

**Algorithm:**

Enabling *Wolfram Alpha* to do its computations required the implementation of tens of thousands of algorithms. Some are as simple as the quadratic formula; others are among the most sophisticated intellectual actions of our time. These algorithms were assembled under the help of *mathematica*.

*Mathematica* is a remarkably efficient programming language in which complex algorithms can be implemented. Complex computational processes can be represented using arbitrarily structured symbolic expressions that are easy for those who don’t know programming. As a result, the five million lines of *Mathematica* code that make up *Wolfram Alpha* are equivalent to many tens of millions of lines of code in a lower-level language like C or Java.

*Mathematica* was the starting point for building *Wolfram Alpha* that made use of a comparable number of its built in algorithms that are considered as some of the most sophisticated ever developed, and then added to it additional algorithms. These algorithms cover wide areas including logical, numerical, graphical, symbolic, and other computations.

Wolfram’s team manually entered, and in some cases automatically pulled in, masses of raw factual data about various fields of knowledge, plus models and algorithms for doing computations with the data. By building all of this in a modular fashion on top of the *Mathematica* engine, they have built a system that is able to actually synthesize sophisticated computations from simple computations over vast data sets representing real-world knowledge.

*Wolfram Alpha* would have been much difficult to be made without *Mathematica. In fact the easiest way to create **Wolfram Alpha* without *mathematica* is to write *mathematica*, and this has been done in the past 23 years.* ** *

**How to use it:**** **

Enter to this website http://www.wolframalpha.com then type in the textbox the required question to be solved. If the “Show Steps” button is pressed, then a step by step explanation of how the answer is computed would be shown.

**Final thoughts:**

There is no doubt that that *Wolfram alpha* is one of the world’s most successful data mining projects ever developed. Despite winning the world’s best project in 2009, there are still many questions to be answered. There is the question of how it will be able to keep up with all the new knowledge in the world. And there is the question of bias; is there any risk of bias in the answers the system gives because all the knowledge is entered by Wolfram’s team? There is not necessarily one right answer — there are valid alternative perspectives and there are potential biases in the answers one might come up with, depending on the data sources used to compute them.

*Wolfram Alpha* will continue to grow and will begin to see some interesting new intelligent applications. As of now, *Wolfram Alpha* contains 10+ trillion pieces of data, 50,000+ types of algorithms and models, and linguistic capabilities for 1000+ domains. Built with *Mathematica*—which is itself the result of more than 20 years of development at Wolfram Research—*Wolfram Alpha*‘s core code base now exceeds 5 million lines of symbolic *Mathematica* code. Running on supercomputer-class compute clusters, *Wolfram Alpha* makes extensive use of the latest generation of web and parallel computing technologies, including webMathematica and gridMathematica.

**References:**

- http://www.wolframalpha.com/faqs.html
- http://www.wolframalpha.com/alphahistory.html
- http://ebiquity.umbc.edu/blogger/category/datamining/
- http://blog.wolframalpha.com/2009/05/01/the-secret-behind-the-computational-engine-in-wolframalpha/

** **