Add LSTM vs CNN timeseries classification example for FordA dataset

[gsklavounakos]

This PR adds a new example under 'examples/timeseries/' that compares LSTM and 1D CNN models for univariate timeseries classification on the FordA dataset from the UCR/UEA archive.

Highlights:

• Uses LSTM and 1D CNN architectures under identical training settings.
• Includes preprocessing, model definition, training with early stopping and checkpointing.
• Visualizes training/validation accuracy and loss for both models.
• Evaluates final test accuracy and loss.
• Models and plots are saved locally.

Tested with:

• Python 3.10.8
• TensorFlow 2.15+
• CPU and GPU (oneDNN optimization enabled)

Files Added:

• 'examples/timeseries/lstm_vs_cnn_timeseries_classification.py'
• 'examples/timeseries/md/lstm_vs_cnn_timeseries_classification.md'

The example follows Keras-IO educational example standards, including model structure, visualization, and reproducibility, is self-contained, and has been tested locally.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.