From 4a474d0625c9827f4797040e62214bb3dd64390d Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Thu, 24 May 2018 11:21:09 +0200 Subject: [PATCH] [NN] Added explanation for second environmental feedback loop in each example Signed-off-by: Jim Martens --- neural-networks/seminarpaper.tex | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/neural-networks/seminarpaper.tex b/neural-networks/seminarpaper.tex index f07706c..d150627 100644 --- a/neural-networks/seminarpaper.tex +++ b/neural-networks/seminarpaper.tex @@ -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 networks (MNN). Any artifical neural network (ANN) or simply neural network 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 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 \(w_i\) 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 @@ -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 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 -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. The neurons within the vicinity of these sources only update their weights