From 08a1f340c1403ac534be9c06e2663c8ef8168fd6 Mon Sep 17 00:00:00 2001 From: Extraltodeus Date: Wed, 20 Mar 2024 18:34:06 +0100 Subject: [PATCH] Update README.md --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 8981ad6..5bffee9 100644 --- a/README.md +++ b/README.md @@ -121,6 +121,8 @@ Too much forward will overreach your general meaning and become more unpredictab I make these nodes to try to understand things deeper. My maths can sometimes be wrong. Everything I do is self-taught with an overly top-to-bottom approach. +Some things like the fact that I'm not turning the cosine similarity score into a linear value might look like an oversight but doing so tends to diminish the effect of the node too strongly and is therefore a deliberate choice. + I feel that what I have done might also be done by tweaking the activation functions but I haven't got that far. Yet. Also kittens seems immune to this transformation and inherits little suits before turning into AI chaos.