Link Details

Wow, this article contains some serious factual errors. I would highly recommend looking elsewhere for information on artificial neural networks.

" The main types of training are supervised and unsupervised training. Supervised training is when we know exactly what we want to output from certain inputs and perform the training iterations ourselves, manually.

Unsupervised training is when we automate a training set based on past experience, for example, if the network was to learn how to play chess and it is beaten, we want the network to learn from its mistake and train it with the preferred response or output. "

Yikes, wrong and wrong! It's time to go back to the comp.ai.neural-nets FAQ.

"Neural networks take in binary digits and output fits (fuzzy bits) which is a number between 0 and 1 but never absolute (e.g. 0.4323, 0.9, 0.1). "

Ouch! Neural networks can accept as input different types of data, and not all neural networks output numbers between 0 and 1.

PredictorX, you may want to post a comment in the actual site of the article, as the author is not likely reading this to reply to you.