LSTM-Demo: Bidirectional LSTM with TensorFlow on the Sonar Dataset

LSTM-Demo is a compact, runnable example that trains a bidirectional Long Short-Term Memory (LSTM) network with TensorFlow and Keras on the classic Sonar dataset.

The Sonar dataset is a well-known binary classification benchmark: each sample has 60 numeric features from sonar returns, and the task is to tell metal cylinders (mines) from rocks. It is small enough to train quickly while still showing a full pipeline.

A bidirectional LSTM reads the input sequence in both directions, which can help the model use context from the whole sequence. The demo is intended as a teaching example you can run, read, and modify. It is archived on Zenodo with a citable DOI.

DOI: https://doi.org/10.5281/zenodo.20672929