|
|
|
/*! @file
|
|
|
|
|
|
|
|
@id $Id$
|
|
|
|
*/
|
|
|
|
// 1 2 3 4 5 6 7 8
|
|
|
|
// 45678901234567890123456789012345678901234567890123456789012345678901234567890
|
|
|
|
|
|
|
|
#include <matrix.hxx>
|
|
|
|
|
|
|
|
/** @mainpage Neural Network with Hidden Layers
|
|
|
|
|
|
|
|
@section neuro-intro Overview
|
|
|
|
|
|
|
|
A complex neural network can be imitiated as a vector @c I of @c i
|
|
|
|
input values, a vector @c O of @c o output values and any number
|
|
|
|
@c l of hidden layers, where each of them contains @c h
|
|
|
|
neurons.
|
|
|
|
|
|
|
|
A neural network with double precision is inistialized as:
|
|
|
|
@code
|
|
|
|
NeuroNet<double, i, o, l+1, h> net;
|
|
|
|
@endcode
|
|
|
|
|
|
|
|
@dot
|
|
|
|
digraph g {
|
|
|
|
rankdir=LR;
|
|
|
|
ranksep=1.5;
|
|
|
|
subgraph clusterInput {
|
|
|
|
label="Input Layer";
|
|
|
|
I1 [label=<I<SUB>1</SUB>>];
|
|
|
|
I2 [label=<I<SUB>2</SUB>>];
|
|
|
|
Ix [label=<I<SUB>…</SUB>>];
|
|
|
|
Ii [label=<I<SUB>i</SUB>>];
|
|
|
|
}
|
|
|
|
subgraph clusterHidden1 {
|
|
|
|
label="First Hidden Layer";
|
|
|
|
H11 [label=<H<SUB>11</SUB>>];
|
|
|
|
H12 [label=<H<SUB>12</SUB>>];
|
|
|
|
H1x [label=<H<SUB>1…</SUB>>];
|
|
|
|
H1h [label=<H<SUB>1h</SUB>>];
|
|
|
|
}
|
|
|
|
subgraph clusterHidden2 {
|
|
|
|
label="Second Hidden Layer";
|
|
|
|
H21 [label=<H<SUB>21</SUB>>];
|
|
|
|
H22 [label=<H<SUB>22</SUB>>];
|
|
|
|
H2x [label=<H<SUB>2…</SUB>>];
|
|
|
|
H2h [label=<H<SUB>2h</SUB>>];
|
|
|
|
}
|
|
|
|
subgraph clusterHiddenx {
|
|
|
|
label="More Hidden Layers";
|
|
|
|
Hx1 [label=<H<SUB>…1</SUB>>];
|
|
|
|
Hx2 [label=<H<SUB>…2</SUB>>];
|
|
|
|
Hxx [label=<H<SUB>……</SUB>>];
|
|
|
|
Hxh [label=<H<SUB>…h</SUB>>];
|
|
|
|
}
|
|
|
|
subgraph clusterHiddenl {
|
|
|
|
label="Last Hidden Layer";
|
|
|
|
Hl1 [label=<H<SUB>l1</SUB>>];
|
|
|
|
Hl2 [label=<H<SUB>l2</SUB>>];
|
|
|
|
Hlx [label=<H<SUB>l…</SUB>>];
|
|
|
|
Hlh [label=<H<SUB>lh</SUB>>];
|
|
|
|
}
|
|
|
|
subgraph clusterOutput {
|
|
|
|
label="Output Layer";
|
|
|
|
O1 [label=<O<SUB>1</SUB>>];
|
|
|
|
O2 [label=<O<SUB>2</SUB>>];
|
|
|
|
Ox [label=<O<SUB>…</SUB>>];
|
|
|
|
Oo [label=<O<SUB>o</SUB>>];
|
|
|
|
}
|
|
|
|
I1 -> { H11; H12; H1x; H1h; }
|
|
|
|
I2 -> { H11; H12; H1x; H1h; }
|
|
|
|
Ix -> { H11; H12; H1x; H1h; }
|
|
|
|
Ii -> { H11; H12; H1x; H1h; }
|
|
|
|
H11 -> { H21; H22; H2x; H2h; }
|
|
|
|
H12 -> { H21; H22; H2x; H2h; }
|
|
|
|
H1x -> { H21; H22; H2x; H2h; }
|
|
|
|
H1h -> { H21; H22; H2x; H2h; }
|
|
|
|
H21 -> { Hx1; Hx2; Hxx; Hxh; }
|
|
|
|
H22 -> { Hx1; Hx2; Hxx; Hxh; }
|
|
|
|
H2x -> { Hx1; Hx2; Hxx; Hxh; }
|
|
|
|
H2h -> { Hx1; Hx2; Hxx; Hxh; }
|
|
|
|
Hx1 -> { Hl1; Hl2; Hlx; Hlh; }
|
|
|
|
Hx2 -> { Hl1; Hl2; Hlx; Hlh; }
|
|
|
|
Hxx -> { Hl1; Hl2; Hlx; Hlh; }
|
|
|
|
Hxh -> { Hl1; Hl2; Hlx; Hlh; }
|
|
|
|
Hl1 -> { O1; O2; Ox; Oo; }
|
|
|
|
Hl2 -> { O1; O2; Ox; Oo; }
|
|
|
|
Hlx -> { O1; O2; Ox; Oo; }
|
|
|
|
Hlh -> { O1; O2; Ox; Oo; }
|
|
|
|
}
|
|
|
|
@enddot
|
|
|
|
|
|
|
|
@section neuro-forward Forward Propagation
|
|
|
|
|
|
|
|
The connections between two layers can be modelled as a
|
|
|
|
Matrix. Then Matrix H<sub>1</sub> contains the weights from @c I
|
|
|
|
to the first hidden layer, @c H<sub>2</sub> from the first to the
|
|
|
|
second, and so on, until @c H<sub>l+1</sub> contains the weights
|
|
|
|
from layer @c l to the output @c O.
|
|
|
|
|
|
|
|
The output vector is then calculated as:
|
|
|
|
O = I × H<sub>1</sub> × H<sub>2</sub> × H<sub>…</sub> × H<sub>l+1</sub>
|
|
|
|
|
|
|
|
@code
|
|
|
|
const size_type i(4);
|
|
|
|
const size_type o(2);
|
|
|
|
NeuroNet<double, i, o> net;
|
|
|
|
Matrix<1, i> input(1.0, 2.0, 0.0, -1.0);
|
|
|
|
Matrix<1, o> output = net(input);
|
|
|
|
@endcode
|
|
|
|
|
|
|
|
@section neuro-backward Back Propagation
|
|
|
|
|
|
|
|
|
|
|
|
*/
|
|
|
|
template
|
|
|
|
<typename TYPE,
|
|
|
|
size_t INPUT_LAYERS,
|
|
|
|
size_t OUTPUT_LAYERS,
|
|
|
|
size_t HIDDEN_LAYERS = INPUT_LAYERS+OUTPUT_LAYERS,
|
|
|
|
size_t HIDDEN_LAYER_SIZE = INPUT_LAYERS+OUTPUT_LAYERS>
|
|
|
|
class NeuroNet {
|
|
|
|
};
|