libeblearn
ebl::lenet5< T, Tstate > Class Template Reference

#include <ebl_machines.h>

Inheritance diagram for ebl::lenet5< T, Tstate >:
ebl::net_cscscf< T, Tstate > ebl::layers< T, Tstate > ebl::module_1_1< T, Tstate, Tstate > ebl::module

List of all members.

Public Member Functions

 lenet5 (parameter< T, Tstate > &prm, intg image_height, intg image_width, intg ki0, intg kj0, intg si0, intg sj0, intg ki1, intg kj1, intg si1, intg sj1, intg hid, intg output_size, bool norm=false, bool mirror=false, bool tanh=false, bool shrink=false, bool diag=false)

Detailed Description

template<typename T, class Tstate = bbstate_idx<T>>
class ebl::lenet5< T, Tstate >

create a new instance of net-cscscf implementing a LeNet-5 type convolutional neural net. This network has regular sigmoid units on the output, not an extra RBF layer as described in the Proc. IEEE paper. The network has 6 feature maps at the first layer and 16 feature maps at the second layer with a connection matrix between feature maps as described in the paper. Arguments: {

       <image-height> <image-width>: height and width of input image
       <ki0> <kj0>: height and with of convolutional kernel, first layer.
       <si0> <sj0>: subsampling ratio of subsampling layer, second layer.
       <ki1> <kj1>: height and with of convolutional kernel, third layer.
       <si1> <sj1>: subsampling ratio of subsampling layer, fourth layer.
       <hid>: number of hidden units, fifth layer
       <output-size>: number of output units
       <net-param>: idx1-ddparam that will hold the trainable parameters
                    of the network
      

} example { (setq p (new idx1-ddparam 0 0.1 0.02 0.02 80000)) (setq z (new-lenet5 32 32 5 5 2 2 5 5 2 2 120 10 p)) }


The documentation for this class was generated from the following files: