The VGA example generates a 320x240 diffusion-limited-aggregation (DLA) on Altera DE2 board. A DLA is a clump formed by sticky particles adhering to an existing structure. In this design, we start with one pixel at the center of the screen and allow a random walker to bounce around the screen until it hits the pixel at the center. It then sticks and a new walker is started randomly at one of the 4 corners of the screen. The random number generators for x and y steps are XOR feedback shift registers (see also Hamblen, Appendix A). The VGA driver, PLL, and reset controller from the DE2 CDROM are necessary to compile this example. Note that you must push KEY0 to start the state machine.
Batch version of the back-propagation algorithm.
％ Given a set of corresponding input-output pairs and an initial network
％ [W1,W2,critvec,iter]=batbp(NetDef,W1,W2,PHI,Y,trparms) trains the
％ network with backpropagation.
％
％ The activation functions must be either linear or tanh. The network
％ architecture is defined by the matrix NetDef consisting of two
％ rows. The first row specifies the hidden layer while the second
％ specifies the output layer.
％
This function calculates Akaike s final prediction error
％ estimate of the average generalization error.
％
％ [FPE,deff,varest,H] = fpe(NetDef,W1,W2,PHI,Y,trparms) produces the
％ final prediction error estimate (fpe), the effective number of
％ weights in the network if the network has been trained with
％ weight decay, an estimate of the noise variance, and the Gauss-Newton
％ Hessian.
％
