Bayesian VS Neural Networks

Machine learning is an exciting area in computer science. In this post I will show you how to use a neural network to learn trends from some data that you have and then classify some new data. This has many applications like detecting the language of a written text, hand written character recognition, etc.

For this post I will be using Fast Artificial Neural Network (FANN). The first step is to install the library. In Ubuntu, you can install it using the repositories with this command:

sudo apt-get install libfann1-dev

Once the library is installed, you can write a simple program to learn some patterns.

Lets see some of the included examples. First, copy them to a writeable folder:

cd ~ mkdir libfannSamples cp /usr/share/doc/libfann1-dev/examples/* libfannSamples

Now let’s compile the examples.

cd libfannSamples make clean;make

We are ready to train a neural network. I will use the included example to learn the exclusive OR function. First, I will show you how you can define the data for learning, in this case, the exclusive OR function. This is the content of the xor.data file.

The first row defines the format of the file. In this case, it says that there are 4 data pairs, with 2 inputs and 1 output. The next rows represent the data itself, which in this case is the exclusive OR function, considering that -1 is false and 1 is true. For each data pair, the first line represents the inputs and the next line, the outputs for those inputs.

Source: Sebastian Montabone

You might also like:

Jeff Hawkins on Artificial Intelligence - Part 5/5
Jeff Hawkins on Artificial Intelligence - Part 5/5
Spike Rate Adaptation Model
Spike Rate Adaptation Model

I read a lot about it...

2005-01-15 02:25:04 by JohnPaul

I've been to China... just briefly...
But since I'm part of the business structure that offshores jobs there... I'm concerned.
I'm not against doing business with China. I'm against a non-regulated, highly tilted bias in China's favor. IP laws for instance. China signed on to honor copyright of music and software - they don't enforce it. Again, they are very 1950s. So, if we have to buy HERO (the movie) for $19.00 where royalties make it back to Zhigy (actress) and friends but yet, they get to buy Starwars for 15 yuan (that's about $2.00 US) but never pay a cent in royalty. That's unfair.
Where they prop up is that we get goods very cheap from China - one reason that exchange rate is go beneficial is because China cannot float their currency on the international market...

Woodhead Publishing To Launch Handbook Of Membrane Reactors: Volume 1  — Azom.com
Woodhead Publishing are launching the first volume of a new Handbook of membrane reactors Membrane reactors are increasingly replacing conventional separation, process and conversion technologies across a wide range of applications. ... Finally, part ...

Related posts:

  1. Bias variance Neural Networks
  2. Regression VS neural networks
  3. AI Junkie Neural Networks
  4. Language Neural networks