Fine-tuning Stacked AEs
From Ufldl
(→Recap of the Backpropagation Algorithm) |
|||
| Line 16: | Line 16: | ||
= - (\nabla_{a^{n_l}}J) \bullet f'(z^{(n_l)}) | = - (\nabla_{a^{n_l}}J) \bullet f'(z^{(n_l)}) | ||
\end{align}</math> | \end{align}</math> | ||
| - | ::(When using softmax regression, the softmax layer has <math>\nabla J = \theta^T(I-P)</math> where <math>I</math> is the input labels and <math>P</math> is the | + | ::(When using softmax regression, the softmax layer has <math>\nabla J = \theta^T(I-P)</math> where <math>I</math> is the input labels and <math>P</math> is the vector of conditional probabilities.) |
: 3. For <math>\textstyle l = n_l-1, n_l-2, n_l-3, \ldots, 2</math> | : 3. For <math>\textstyle l = n_l-1, n_l-2, n_l-3, \ldots, 2</math> | ||
::Set | ::Set | ||
