Formatting, and removed region.

Changed random weight deltas to be gaussian with a sigma of 0.01 inst…

…ead of 0.1. This matches SharpNEAT 2.x. The intention for the SharpNEAT 4.0 release was to keep parameters such as these identical to SharpNEAT 2.x, so that the core neuroevolution algorithm is as close as possible between the two versions, despite the big architectural overhaul.

This allows us to compare the performance/efficacy of 2.x and 4.x, to give some assurance that there isn't some bug/flaw in the 4.x code base that impacts performance.

Future releases can then be free to explore tuning of hyper parameters and such, once we have established that 4.x performs at least as well as 2.x.

Added RepositoryUrl and PackageReadmeFile entries.

Redzen nuget update: 9.1.0 -> 9.1.1

Merge branch 'master' of https://github.com/colgreen/sharpneat

Updated redzen nuget to 9.0.0.

Update package version: 2.4.1.3 -> 2.4.1.4

Default activation function changed from LogisticFunctionSteep to Lea…

…kyReLU or the following experiments: BinaryElevenMultiplexerExperiment, BinarySixMultiplexerExperiment, BinaryThreeMultiplexerExperiment, GenerativeFnRegressionExperiment, Xor.

This is based on evidence that LeakyReLU leads to better performance on these experiments; see http://sharpneat.sourceforge.net/research/activation-fn-review/activation-fn-review.html

Efficacy sampler: Enabled gcServer setting; this seems to result in a…

… significant performance improvement; it may also prevent a sporadic ExecutionEngine exception.

Default activation function reverted to SteepenedSigmoid. This will b…

…e the default for release 2.3.0. A later version may change this.