v1.1.0

- `ActivationFunction`:
  - Added field `flatSpot` for `derivativeEntryWithFlatSpot()`.
  - Added `ActivationFunctionLinear`.
  - `ActivationFunctionSigmoid`: activation with bounds (-700 .. 700).
- Improved collections and numeric extensions.
- Improved `DataStatistics` and add `CSV` generator.
- `Signal`:
  - Added SIMD related operations.
  - Added: `computeSumSquaresMean`, `computeSumSquares`, `valuesAsDouble`.
  - Set extra values (out of length range): `setExtraValuesToZero`, `setExtraValuesToOne`, `setExtraValues`.
  - Improved documentation.
- `Sample`:
  - Input/Output statistics and proximity.
- Added `SamplesSet`:
  - With per set computed `defaultTargetGlobalError`.
  - Automatic `removeConflicts`.
- `Training`:
  - Split into `Propagation` and `ParameterStrategy`, allowing other algorithms.
  - Added `Backpropagation` with SIMD, smart learning rate and smart momentum.
  - Added `iRprop+`.
  - Added `TrainingLogger`.
  - Added `selectInitialANN`.
- `ANN`:
  - Optional bias neuron.
  - Allow different `ActivationFunction` for each layer.

pubspec.yaml

@@ -1,6 +1,6 @@
 name: eneural_net
 description: AI Library to create efficient Artificial Neural Networks. Computation uses SIMD (Single Instruction Multiple Data) to improve performance.
-version: 1.0.2
+version: 1.1.0
 homepage: https://eneural.net/
 
 environment: