guillaume-chevalier/seq2seq-signal-prediction resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1081 stars · 286 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

learning-resource · maturity maintenance

machine-learning deep-learning machine-learning deep-learning tutorials time-series python cross-platform seq2seq rnn tensorflow time-series-forecasting jupyter-notebook encoder-decoder tutorial-exercises

Member repositories

For agents

markdown · JSON · MCP: product_card(name="guillaume-chevalier/seq2seq-signal-prediction")