Thinc

✨ Major features and improvements
- **NEW:** Add several useful higher-order functions, including `layerize` and `metalayerize` decorators to turn functions into weightless layers.
- **NEW:** Add batch normalization layer.
- **NEW:** Add residual layer using pre-activation approach.
- Simplify model setup and initialization.
- Add `ELU` layer.

🔴 Bug fixes
- The `AveragedPerceptron` class can now continue training after model loading. Previously, the weights were zeroed for each feature as soon as it was updated. This affected [spaCy](https://github.com/explosion/spaCy) users, especially those adding new classes to the named entity recognizer.

📖 Documentation and examples
- Add [CNN tagger example](https://github.com/explosion/thinc/blob/master/examples/cnn_tagger.py).

✨ Major features and improvements
- **NEW**: Add `thinc.neural` to develop neural networks for [spaCy](https://github.com/explosion/spaCy).
- Introduce support for Affine, Maxout, ReLu and Softmax vector-to-vector layers.
- Introduce support for efficient static word embedding layer with projection matrix and per-word-type memoisation.
- Introduce support for efficient word vector convolution layer, which also supports per-word-type memoisation.
- Introduce support for `MeanPooling`, `MaxPooling` and `MinPooling`. Add `MultiPooling` layer for concatenative pooling.
- Introduce support for annealed dropout training.
- Introduce support for classical momentum, Adam and Eve optimisers.
- Introduce support for averaged parameters for each optimiser.

⚠️ Backwards incompatibilities

The `Example` class now holds a pointer to its `ExampleC` struct, where previously it held the struct value. This introduces a small backwards incompatibility in spaCy.