Differences

This shows you the differences between two versions of the page.

--- data_mining:neural_network:neurons [2017/08/13 11:38] – [Rectified Linear Neurons] phreazer
+++ data_mining:neural_network:neurons [2017/08/19 17:42] – [Rectified Linear Neurons] phreazer
@@ Line 74: / Line 74: @@
 $z=b+\sum_{i} x_{i} w_{i}$
-$y = \begin{cases} z, & \text{if } z > 0 \\ 0, & \text{otherwhise}\end{cases}$
+$y = \begin{cases} z, & \text{if } z > 0 \\ 0, & \text{otherwhise}\end{cases} = \max(0,z)$
 Above 0, it is linear, at 0 it is 0
+Faster computation, since slope doesn't get very small/large.
@@ Line 92: / Line 95: @@
 $\text{lim}_{(z->∞)} \frac{1}{1+e^{-z}} = 1$
-==== Softmax group ====
+Switch from Sigmoid to ReLU lead to performance improvement (Slope of Sigmoid gradually shrinks to zero).
+===== tanh =====
+Works better than Sigmoid function.
+$y = \frac{e^{z}-e^{-z}}{e^{z}+e^{-z}}$
+Centering of data to 0.
+Exception: Output layer, since output should be in [0,1].
+===== Softmax group =====
+Logistic function output is used for the classification between two target classes 0/1. Softmax function is generalized type of logistic function that can output a **multiclass** categorical **probability distribution**.
 Derivates:
@@ Line 138: / Line 154: @@
 Also possible for rectified linear units: Output is treated as the poisson rate for spikes.
-===== Softmax =====
-Logistic function output is used for the classification between two target classes 0/1. Softmax function is generalized type of logistic function that can output a multiclass categorical probability distribution.