This link has been bookmarked by 3 people . It was first bookmarked on 21 Aug 2008, by Doug Y'barbo.
-
04 Jul 13
-
17 Jan 13
-
A nonlinear problem
Consider again the best linear fit we found for the car data. Notice that the data points are not evenly distributed around the line: for low weights, we see more miles per gallon than our model predicts. In fact, it looks as if a simple curve might fit these data better than the straight line. We can enable our neural network to do such curve fitting by giving it an additional node which has a suitably curved (nonlinear) activation function. A useful function for this purpose is the S-shaped hyperbolic tangent (tanh) function (Fig. 1).
-
-
19 Nov 11
-
additional node which has a suitably curved (nonlinear) activation function
-
all non-input neural network units have such a bias weight.
-
bias weights shift the tanh function in the x- and y-direction
-
other two weights scale it along those two directions
-
too large a hidden layer - or too many hidden layers - can degrade the network's performance
-
any function can be expressed as a linear combination of tanh functions: tanh is a universal basis function
-
two classes of activation functions commonly used in neural networks are the sigmoidal (S-shaped) basis functions (to which tanh belongs), and the radial basis functions
-
Would you like to comment?
Join Diigo for a free account, or sign in if you are already a member.