*first ann project
This is a simple ANN Model codes(Perceptron, LVQ, BP). Basicly im trying to teach ann models blackjack data sets. When problem is simple lvq and perceptron can learn fast but BP is uses too much procedure, in this problem BP needs 50+ iteration to learn but LVQ and Perceptron learns in 10 iteration so easily.
Blackjack, also known as twenty-one, is a comparing card game between usually several players and a dealer, where each player in turn competes against the dealer, but players do not play against each other. It is played with one or more decks of 52 cards, and is the most widely played casino banking game in the world. The objective of the game is to beat the dealer in one of the following ways:
Get 21 points on the player's first two cards (called a "blackjack" or "natural"), without a dealer blackjack;
Reach a final score higher than the dealer without exceeding 21; or
Let the dealer draw additional cards until their hand exceeds 21.
http://imageshack.com/a/img924/3125/zlRRPU.png
As you can see with 10 iteration lvq and perceptron can handle with this dataset