2martens/uni
1
0
Fork 0
mirror of https://github.com/2martens/uni.git synced 2026-05-06 11:26:25 +02:00
Code Releases Activity

[NN] Added explanation for second environmental feedback loop in each example

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2018-05-24 11:21:09 +02:00
parent 1578ef4577
commit 4a474d0625
1 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
neural-networks/seminarpaper.tex
View File

@ -321,7 +321,8 @@ neural networks the structure of these networks is described first. Linearly-mod
neural networks (LMNN) are a specific variant of modulated neural neural networks (LMNN) are a specific variant of modulated neural
networks (MNN). Any artifical neural network (ANN) or simply neural network networks (MNN). Any artifical neural network (ANN) or simply neural network
in the context of Computer Science can become a modulated neural network by in the context of Computer Science can become a modulated neural network by
adding a neuromodulator layer. adding a neuromodulator layer. This neuromodulator layer is the second
environmental feedback loop mentioned earlier.
Toutounji and Pasemann describe a variant of this layer that uses neuromodulator Toutounji and Pasemann describe a variant of this layer that uses neuromodulator
cells (NMCs). Each NMC produces a specific type of neuromodulator (NM) and cells (NMCs). Each NMC produces a specific type of neuromodulator (NM) and
@ -381,6 +382,11 @@ synapse. Weight changes can happen at any time step. Therefore the intrinsic wei
change probability has to be very small. Should a weight change occur a new weight change probability has to be very small. Should a weight change occur a new weight
\(w_i\) is chosen randomly from the interval \([W_i^{min}, W_i^{max}]\). \(w_i\) is chosen randomly from the interval \([W_i^{min}, W_i^{max}]\).
The weight change probability \(p_i^w\) tells the network when to learn and leaves
room for variation as it is a probability and not a binary learn/do not learn
situation. Within this example this probability is the so called second environmental
feedback loop.
\[ \[
p_i^w = min(M_i, c(t, x_i, y_i)) \cdot W_i,\; 0 < W_i \lll 1 p_i^w = min(M_i, c(t, x_i, y_i)) \cdot W_i,\; 0 < W_i \lll 1
@ -445,7 +451,9 @@ the previously eaten food was nutritious (1) or poisonous (-1). If they are
not active their value is zero. As soon as the sources are activated the neuromodulators not active their value is zero. As soon as the sources are activated the neuromodulators
fill a space within a radius of 1.5 units of distance from the source and potentially fill a space within a radius of 1.5 units of distance from the source and potentially
trigger weight changes of neurons inside the radius. The strength of the neuromodulators trigger weight changes of neurons inside the radius. The strength of the neuromodulators
is decreasing with further distance from the source. is decreasing with further distance from the source. The sources are the second
environmental feedback loop in this example as they tell the network or a part of
it when to learn.
This explanation should suffice for the general understanding of their method. This explanation should suffice for the general understanding of their method.
The neurons within the vicinity of these sources only update their weights The neurons within the vicinity of these sources only update their weights