Add recurrent and mlp models

[jdb78]

Description

This PR adds a simple recurrent and MLP network

Checklist

• Linked issues (if existing)
• Amended changelog for large changes (and added myself there as contributor)
• Added/modified tests
• Used pre-commit hooks when committing to ensure that code is compliant with hooks. Install hooks with pre-commit install.
  To run hooks independent of commit, execute pre-commit run --all-files

Make sure to have fun coding!

[codecov-io]

Codecov Report

Merging #380 (1be6e6c) into master (48179d2) will increase coverage by 0.33%.
The diff coverage is 94.07%.

@@            Coverage Diff             @@
##           master     #380      +/-   ##
==========================================
+ Coverage   90.74%   91.08%   +0.33%     
==========================================
  Files          20       22       +2     
  Lines        3372     3487     +115     
==========================================
+ Hits         3060     3176     +116     
+ Misses        312      311       -1     

Flag	Coverage Δ
cpu	91.08% <94.07%> (+0.33%)	⬆️
pytest	91.08% <94.07%> (+0.33%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
pytorch_forecasting/__init__.py	100.00% <ø> (ø)
pytorch_forecasting/models/deepar/__init__.py	98.50% <ø> (ø)
pytorch_forecasting/models/base_model.py	88.34% <78.37%> (+0.17%)	⬆️
pytorch_forecasting/models/__init__.py	100.00% <100.00%> (ø)
pytorch_forecasting/models/mlp/__init__.py	100.00% <100.00%> (ø)
pytorch_forecasting/models/rnn/__init__.py	100.00% <100.00%> (ø)
...ing/models/temporal_fusion_transformer/__init__.py	96.94% <100.00%> (+1.04%)	⬆️
pytorch_forecasting/metrics.py	93.92% <0.00%> (+0.25%)	⬆️
... and 1 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 48179d2...1be6e6c. Read the comment docs.