# guillaume-chevalier/seq2seq-signal-prediction

Signal forecasting with a Sequence-to-Sequence (seq2seq) Recurrent Neural Network (RNN) model in TensorFlow - Guillaume Chevalier

Repository: https://github.com/guillaume-chevalier/seq2seq-signal-prediction
Canonical: https://ross.abutalabs.com/products/seq2seq-signal-prediction
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: seq2seq, tensorflow, tensorflow-tutorials, python
Last push: 2023-03-25T00:33:48+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3442, "days_push": 1258, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1081, forks 286 (observed 2026-08-28T04:03:30.669566+00:00)

## What it is
A Jupyter notebook tutorial with four graded exercises for learning to build Encoder-Decoder Sequence-to-Sequence RNN models in TensorFlow for time series signal forecasting. It includes toy datasets, a Python script version, and Google Colab support.

## Use cases
- learn how to code seq2seq encoder-decoder RNNs
- forecast time series signals with a neural network
- practice TensorFlow RNN exercises with increasing difficulty
- run a seq2seq forecasting notebook in Google Colab
- understand encoder-decoder architectures without attention
- adapt seq2seq models to other tasks like NLP

## When to choose
- you want a hands-on, exercise-driven tutorial for seq2seq RNNs in TensorFlow
- you are learning time series forecasting with recurrent neural networks
- you prefer runnable notebooks with toy datasets and Colab GPU support

## When to avoid
- you need a production-ready forecasting library or maintained model code
- you want modern TensorFlow 2.x or PyTorch implementations
- you need attention-based transformers rather than basic seq2seq RNNs

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, tutorials, time-series
- platform: python, cross-platform
- tags: seq2seq, rnn, tensorflow, time-series-forecasting, jupyter-notebook, encoder-decoder, tutorial-exercises

## Member repositories
- guillaume-chevalier/seq2seq-signal-prediction (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:30.669566+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:51:22.182639+00:00, confidence not recorded.
  - readme: https://github.com/guillaume-chevalier/seq2seq-signal-prediction (fetched 2026-08-28T04:03:30.669566+00:00, sha eee2e1943cc0)
- Data as of 2026-08-30T08:39:29.467469+00:00.