[ENH] Added TemporalConvolutionalNetwork in aeon/networks

[lucifer4073]

Reference Issues/PRs

Fixes #2931 .

What does this implement/fix? Explain your changes.

Introduce a robust and modular implementation of Temporal Convolutional Networks (TCN) for sequence modeling in aeon.forecasting.deep_learning.

Does your contribution introduce a new dependency? If yes, which one?

N/A

Any other comments?

As of now, there is a weight normalization layer remaining. Need some clarifications before proceeding with that.

PR checklist

For all contributions

• I've added myself to the list of contributors. Alternatively, you can use the @all-contributors bot to do this for you after the PR has been merged.
• The PR title starts with either [ENH], [MNT], [DOC], [BUG], [REF], [DEP] or [GOV] indicating whether the PR topic is related to enhancement, maintenance, documentation, bugs, refactoring, deprecation or governance.

For new estimators and functions

• I've added the estimator/function to the online API documentation.
• (OPTIONAL) I've added myself as a __maintainer__ at the top of relevant files and want to be contacted regarding its maintenance. Unmaintained files may be removed. This is for the full file, and you should not add yourself if you are just making minor changes or do not want to help maintain its contents.

For developers with write access

• (OPTIONAL) I've updated aeon's CODEOWNERS to receive notifications about future changes to these files.

[aeon-actions-bot]

Thank you for contributing to aeon

I have added the following labels to this PR based on the title: [ enhancement ].
I have added the following labels to this PR based on the changes made: [ networks ]. Feel free to change these if they do not properly represent the PR.

The Checks tab will show the status of our automated tests. You can click on individual test runs in the tab or "Details" in the panel below to see more information if there is a failure.

If our pre-commit code quality check fails, any trivial fixes will automatically be pushed to your PR unless it is a draft.

Don't hesitate to ask questions on the aeon Slack channel if you have any.

PR CI actions

These checkboxes will add labels to enable/disable CI functionality for this PR. This may not take effect immediately, and a new commit may be required to run the new configuration.

• Run pre-commit checks for all files
• Run mypy typecheck tests
• Run all pytest tests and configurations
• Run all notebook example tests
• Run numba-disabled codecov tests
• Stop automatic pre-commit fixes (always disabled for drafts)
• Disable numba cache loading
• Push an empty commit to re-run CI checks

[hadifawaz1999]

I left lots of comments here. Generally, you do not have to do keep doing the permute operations between channel and time axes. Networks model assumes always the input_shape parameters is (time, channels) and you do not have to keep doing the permutaiton internally, it is adding operations for no need.

Generally i would like to keep consistency with parameter names with other networks. Like n_filters dilation_rate

[hadifawaz1999]

n_filters in docstring to follow the parameter name, no longer num_channels

[lucifer4073]

n_filters name is failing, because aeon/networks/tests/test_all_networks.py expects n_filters to be int and not list

[lucifer4073]

I plan to use n_blocks instead.

[lucifer4073]

Hi @hadifawaz1999,

Requested changes have been made.