From 24a97f06db775f6ff743c4410cd1e031b860ba3a Mon Sep 17 00:00:00 2001 From: Petr Baudis Date: Wed, 10 Mar 2010 00:39:00 +0100 Subject: [PATCH] tex: Random tweaks --- tex/gostyle.tex | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tex/gostyle.tex b/tex/gostyle.tex index 6f6490a..d9ce2b1 100644 --- a/tex/gostyle.tex +++ b/tex/gostyle.tex @@ -614,7 +614,7 @@ The activity of output layer is then presented as the result. The activation $y_i$ of neuron $i$ from the layer $I$ is computed as \begin{equation} -y_i = f(\sum_{j \in J}{w_{ij} y_j}) +y_i = f\left(\sum_{j \in J}{w_{ij} y_j}\right) \end{equation} where $J$ is the previous layer, while $y_j$ is the activation for neurons from $J$ layer. Function $f()$ is so-called \emph{activation function} @@ -644,7 +644,7 @@ The training set $T$ is then extended by adding the linear combinations: T_\mathit{base} = \{(\vec p_r, \vec s_r) | r \in R\}\\ \end{equation} \begin{equation} -T_\mathit{ext} = \{(\vec p, \vec s) | \exists D \subseteq R : \vec p = \sum_{d \in D}{g_d \vec p_d}, \vec s = \sum_{d \in D}{g_d \vec s_d}\} +T_\mathit{ext} = \left\{(\vec p, \vec s) \,\middle|\, \exists D \subseteq R : \vec p = \sum_{d \in D}{g_d \vec p_d}, \vec s = \sum_{d \in D}{g_d \vec s_d}\right\} \end{equation} TODO zabudovat $g_d$ dovnitr? where $g_d, d \in D$ are random coeficients, so that $\sum_{d \in D}{g_d} = 1$. @@ -846,6 +846,8 @@ Chen Yaoye & $6.0 \pm 1.0$ & $4.0 \pm 1.0$ & $6.0 \pm 1.0$ & $5.5 \pm PCA analysis yielded X, chi-square test... +Kohonen map view. + \subsection{Style Classification} We then tried to apply the NN classifier with linear output function on the dataset -- 2.11.4.GIT