feat: add GaussianNLLLoss

[Bellman281]

Checklist

• Confirmed that cargo run-checks command has been executed.
• Made sure the book is up to date with changes in this PR.

Related Issues/PRs

Part of the PyTorch loss-parity effort, following SoftMarginLoss (#5149),
MarginRankingLoss (#5151), HingeEmbeddingLoss, TripletMarginLoss, and MultiMarginLoss.

Changes

Adds GaussianNLLLoss / GaussianNLLLossConfig, matching torch.nn.GaussianNLLLoss:
0.5 · (log(var) + (input − target)² / var) element-wise, with var clamped to eps
(default 1e-6) and an optional full term 0.5·log(2π) (default off). Composed from existing
ops so autodiff is free. Follows the MarginRankingLoss config/module pattern; added to the
book's loss table.

Testing

Known-answer tests for the base and full = true cases (forward_no_reduction + Mean + Sum)
verified against PyTorch reference values, plus a display test. cargo run-checks passes.

[codecov]

Codecov Report

❌ Patch coverage is 98.79518% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 66.11%. Comparing base (12cba54) to head (94aff2f).
⚠️ Report is 11 commits behind head on main.

Files with missing lines	Patch %	Lines
crates/burn-nn/src/loss/gaussian_nll.rs	98.79%	1 Missing ⚠️

❌ Your project check has failed because the head coverage (66.11%) is below the target coverage (80.00%). You can increase the head coverage or adjust the target coverage.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #5182      +/-   ##
==========================================
+ Coverage   66.03%   66.11%   +0.07%     
==========================================
  Files        1206     1213       +7     
  Lines      183117   183466     +349     
==========================================
+ Hits       120927   121295     +368     
+ Misses      62190    62171      -19     

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.