test+docs: gate 3-input scaling learns + a cloud runbook for free Vivado closure (Refs #1764) - #1914
Merged
Merged
Conversation
…sure (Refs #1764) Stack (V2): the learning gate covered only 2-input tasks. Adds a 3-input (3,5,1) net learning a noisy 3-feature majority task, held-out 55/60 (92%), deterministic -- CI now proves the generator scales along the input dimension, not just depth/width. Vivado path (V1): adds docs/vivado_closure/CLOUD_RUNBOOK.md with concrete steps to run the closure kit on free Vivado ML Standard on an x86-64 Linux/cloud host (build-only; flash the .bit back on the Mac). Free Vivado supports xc7a200t; it just doesn't run on macOS. Refs #1764 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Contributor
|
📓 NotebookLM Notebook linked to this PR
This notebook contains session context, decisions, and artifacts for this work. |
Contributor
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack (V2): the CI learning gate covered only 2-input tasks (XOR-like). Adds a 3-input
(3,5,1)net learning a noisy 3-feature majority task — held-out 55/60 (92%), deterministic — so CI now proves the generator scales along the input dimension, not just depth/width. (3-way parity was too hard for a small net at 72%; majority is the clean, reliable demonstrator.)Vivado path (V1): adds
docs/vivado_closure/CLOUD_RUNBOOK.md— concrete steps to run the closure kit on free Vivado ML Standard on an x86-64 Linux box or cloud instance (AWSt3.xlarge/ GCPe2-standard-4, build-only, no FPGA on the cloud host; copy the.bitback and flash on the Mac). Free Vivado supportsxc7a200t; it just doesn't run on macOS.Context: the open flow already trains XOR on silicon (met-timing + seed-search); Vivado is only for deterministic no-seed-search closure and nets larger than XOR. Refs #1764