Neural networks

2020-01-28 本文已影响0人 spraysss

Layer

input layer
output layer
hidden layer

$a^{(j)}_i$ is "activation" of unit i in layer j
$\Theta^{j}$ is matrix of weights controlling function mapping from layer j to layer j+1

$a^{2}_1=g(\Theta_{10}^{(1)}x_0+\Theta_{11}^{(1)}x_1+\Theta_{12}^{(1)}x_2+\Theta_{13}^{(1)}x_3)$
$a^{2}_2=g(\Theta_{20}^{(1)}x_0+\Theta_{21}^{(1)}x_1+\Theta_{22}^{(1)}x_2+\Theta_{23}^{(1)}x_3)$
$a^{2}_2=g(\Theta_{30}^{(1)}x_0+\Theta_{31}^{(1)}x_1+\Theta_{32}^{(1)}x_2+\Theta_{33}^{(1)}x_3)$
$h_\theta(x)=g(\Theta_{10}^{(1)}a_0+\Theta_{11}^{(1)}a_1+\Theta_{12}^{(1)}a_2+\Theta_{13}^{(1)}a_3)$

if network has $s_j$ units in layer j, $s_{j+1}$ units in layer j+1,then $\Theta^{(j)}$ will be of dimension $s_{j+1}\times (s_j+1)$

Neural networks

Layer

XNOR implement use Neural networks

multi-class classfication use Neural networks

猜你喜欢

热点阅读