Memento-GRU (M-GRU): a delay-aware GRU with Smith predictor and adaptive feedback.
Project description
Memento-GRU (M-GRU)
A minimal, research-friendly package implementing:
- GRU baseline
- Tiny-MLP predictor
- Smith-style delay compensation
- Adaptive feedback gain
- Trainer, CLI, synthetic dataset, and plots
Install (editable)
pip install -e .
Quickstart
mgru train --model gru --epochs 2
mgru train --model mgru --epochs 2 --delay 3
mgru eval --model mgru --ckpt .runs/mgru/latest.pt
mgru plot --run .runs/mgru
See examples/ for Python APIs.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mgru-0.1.0.tar.gz.
File metadata
- Download URL: mgru-0.1.0.tar.gz
- Upload date:
- Size: 7.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1cb3c1064b08d69c354a96318ed497725cfb1a8e44d25c172f43caf63d8f7de5
|
|
| MD5 |
0439a70ea854076d3d3d20f40cb60b1e
|
|
| BLAKE2b-256 |
37e27599a027c4f22346c91aefb2937c73b0926ac2c5d2437e5d9561bb590ab7
|
Provenance
The following attestation bundles were made for mgru-0.1.0.tar.gz:
Publisher:
publish.yml on Naveenkumarar/m-gru
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mgru-0.1.0.tar.gz -
Subject digest:
1cb3c1064b08d69c354a96318ed497725cfb1a8e44d25c172f43caf63d8f7de5 - Sigstore transparency entry: 651424573
- Sigstore integration time:
-
Permalink:
Naveenkumarar/m-gru@e5c5d51f0cb7b3ed68f15038c525507975a99f1e -
Branch / Tag:
refs/tags/v0.1.3 - Owner: https://github.com/Naveenkumarar
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@e5c5d51f0cb7b3ed68f15038c525507975a99f1e -
Trigger Event:
release
-
Statement type:
File details
Details for the file mgru-0.1.0-py3-none-any.whl.
File metadata
- Download URL: mgru-0.1.0-py3-none-any.whl
- Upload date:
- Size: 9.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bf6b9dffc60bb806fd4cae38974f66d0bf7e4ef69a7aa34cc5351037e7cc4ba9
|
|
| MD5 |
9b70fd342ee7a3f3eadb2005d5cf035b
|
|
| BLAKE2b-256 |
a257ac6da4c3f5519e1f3d53a35ffb38e53d05a3262c7531eb52e9090565a195
|
Provenance
The following attestation bundles were made for mgru-0.1.0-py3-none-any.whl:
Publisher:
publish.yml on Naveenkumarar/m-gru
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mgru-0.1.0-py3-none-any.whl -
Subject digest:
bf6b9dffc60bb806fd4cae38974f66d0bf7e4ef69a7aa34cc5351037e7cc4ba9 - Sigstore transparency entry: 651424574
- Sigstore integration time:
-
Permalink:
Naveenkumarar/m-gru@e5c5d51f0cb7b3ed68f15038c525507975a99f1e -
Branch / Tag:
refs/tags/v0.1.3 - Owner: https://github.com/Naveenkumarar
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@e5c5d51f0cb7b3ed68f15038c525507975a99f1e -
Trigger Event:
release
-
Statement type:
