SILOQY RNG needs "conditioning": Variance, etc.- #2

Open
opened 2025-10-08 12:28:39 +02:00 by hjnormey · 3 comments
Owner

The implemented RNG (2) is "too perfect": Variance is low. It is "better-than-NIST".-
THIS is BAD for certain ML functions: Weight init needs simmetry breakage to actually train.-
SO a "conditioner" or variance-injector or similar needs developed.-

The implemented RNG (2) is "too perfect": Variance is low. It is "better-than-NIST".- THIS is BAD for certain ML functions: Weight init needs simmetry breakage to actually train.- SO a "conditioner" or variance-injector or similar needs developed.-
Author
Owner

Prototype at:

PS: Might be applicable into/to "ML-based weight init" via "meta" network (v. ChatGPT): That system ML-d the best init weights based on a "suite" of stat-tests on incoming data, training a "meta" network.-
.. that then provided a better startinf off point for downstream ML.-

Prototype at: - https://claude.ai/chat/533f6f3d-036b-4646-be0c-fdcce91b082d PS: Might be applicable into/to "ML-based weight init" via "meta" network (v. ChatGPT): That system ML-d the best init weights based on a "suite" of stat-tests on incoming data, training a "meta" network.- .. that then provided a better startinf off point for downstream ML.-
Author
Owner
https://chatgpt.com/g/g-p-68bf350bb9748191ad9debe95867c538-siloqy-dolphin/c/68e679cb-4ee8-832b-a814-23015788521b
Author
Owner
More code: - https://grok.com/c/3ffde5db-8e2b-40bd-b018-094c922822d5
Sign in to join this conversation.
No Label
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: hjnormey/siloqy#2
No description provided.