Merged
Conversation
opentaco
changed the title
S0AndS0
approved these changes
Apr 3, 2023
Eugene-hu
approved these changes
Apr 4, 2023
opentaco
added a commit
that referenced
this pull request
Apr 5, 2023
* Add vec_max_upscale_to_u16 * Do max-upscale pruning_scores * Add epoch test log details for u16 pruning_scores * Norm when no max * Added max-upscaling unnormalized handling * Update spec_version to 116
Contributor
|
Main chain upgraded @ block 114,315 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Currently
pruning_scoresare a u16 quantization of normalized emission, which is problematic given ~4096 values and a Pareto distribution of emissions. Currently finney has a max emission of ~11% and a min non-zero emission of ~0.0002% (0.000002), but the lowest u16 quantity is 1/2^16 = 0.000015 (0.0015%).The purpose of
pruning_scoresis to make relative comparisons during registration to determine the neuron to replace, which has the lowestpruning_score. Therefore, it doesn't have to be normalized, so this PR proposes max-upscaling wheremax(pruning_scores) = u16::MAX. So scale scores relative to the max score, so 0.0002/11 = 0.000018 (> 0.000015 u16 min quantity).Assumes that
pruning_scoresis used only for relative comparison, and doesn't have to be normalized.