Great God's Notes: http://ai-start.com/ml2014/html/week4.html#header-n634
8.7 Suppose you have a multi-class classification problem with 10 classes. Your neural network has 3 layers, and the hidden layer (layer 2) has 5 units. Using the one-vs-all method described here, how many elements does Θ(2)
50 55 60√ 66
The multi-class classifier contains ten classes, the activation unit of the third layer is 10 for theta row, the second layer has 5 units, plus a deviation, it is 6 for theta column , the theta dimension should be 10*6