Implementing Backpropagation to predict Tournament Outcome

I'm trying to predict a certain game tournament outcome using backpropagation. The game's mechanics is basically 2 teams, each controlling 5 heroes to destroy the opponent's base. My data structure consists of tables of (11) team's match histories against the other 10 teams. Basically 1 set of tables for each team. The tables contains these inputs:

• The opponent's team ID (integer value - 1 ~ 11)
• The (5) heroes ID used by team A and (5) heroes used by team B (integer value 1 ~ 114)

In total, the input has 11 elements.

The target tables contains values "1" if team A wins and "0" if team B wins.

I'm new to Matlab, so I wasn't sure which tool is best for this problem. I had tried using the nnstart tool but I don't know how to set the tool to use backpropagation. Also I would like to know, should I normalize the data for this problem? Is binary sigmoid the correct activation function to use?

Thanks in advance.