From f182d6b740ce6d441719c5ea9c053474b3befafd Mon Sep 17 00:00:00 2001 From: Dominik Roth Date: Sun, 24 Oct 2021 11:30:25 +0200 Subject: [PATCH] Added a icon (as svg) --- PetriDish.svg | 183 ++++++++++++++++++++++++++++++++++++++++++++++++++ README.md | 5 +- 2 files changed, 187 insertions(+), 1 deletion(-) create mode 100644 PetriDish.svg diff --git a/PetriDish.svg b/PetriDish.svg new file mode 100644 index 0000000..ef9ab0a --- /dev/null +++ b/PetriDish.svg @@ -0,0 +1,183 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/README.md b/README.md index 0a47295..a85c6cd 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,7 @@ # Project PetriDish + +![Logo](/home/dodox/Pictures/Inkscape/PetriDish.svg) + Quick and dirty PoC for the idea behind Project Neuromorph. Combines PonderNet and SparseLinear. PonderNet stolen from https://github.com/jankrepl/mildlyoverfitted/blob/master/github_adventures/pondernet @@ -9,4 +12,4 @@ A neural network comprised of a set of neurons that are connected using a set of We train this net like normal; but we also allow the structure of the synapctic connections to change during training. (Number of neurons remains constant; this is also variable in Neuromorph; Neuromorph will also use more advanced algorithms to decide where to spawn new synapses) In every firing-cycle only a fraction of all neurons are allowed to fire (highest output) all others are inhibited. (In Project Neuromorph this will be less strict; low firing-rates will have higher dropout-chances and we discurage firing thought an additional loss) Based on the PonderNet-Architecture we allow our network to 'think' as long as it wants about a given problem (well, ok; there is a maximum amount of firing-cycles to make training possbile) -The input's and output's of the network have a fixed length. (Project Neuromorph will also allow variable-length outputs like in a RNN) +The input's and output's of the network have a fixed length. (Project Neuromorph will also allow variable-length outputs like in a RNN) \ No newline at end of file