MOD: modified the calculation of jacobian and added new functionality to NeuralNetwork class to support the new jacobian calculation

ADD: added kallman filter learning method (not tested) and random learning method + modifications in neural network to support the new functionality

ADD+MOD+FIX: added new evaluation functions for debug/testing purposes, modified random generation of parameters, fixed the calculation of gradient via backpropagation

ENH: Now it's possible to specify different neuron types for different hidden layers in FullyConnectedFFNs.

ENH: Methods print_* changed for overloaded methods write_*, which make possible writing not only to STDOUT, but also to the file.

ENH + NEW: Implemented the data normalization funcionality to DataSet. Created a new class NormalizationStrategy.

ENH: Only classes belonging to API are now contained in 4neuro.h. All those classes were enclosed in 'lib4neuro' namespace.

ADD: added preliminary version of gradient calculation vie backpropagation, added supporting methods to error classes and learning algorithms utilizing gradient calculation

ENH: Removed both linking and include dependencies from examples => lib4neuro can be used just by linking it and including its header without any external dependencies needed.

FIX: Fixed Boost include dependencies, so the examples don't have to be compiled with Boost include directory.

Updated the first ode example to analyze the correctness of the neural networks assembled by the DESolver
Corrected some examples to reflect the structural changes in the previous commit

Updated the structure and functionality of NeuralNEtwork class to account for the changes in connections and neurons.
Updated the logic in DESolver to account for the changes in NeuralNetwork

edited the first ode example to use the new DESolver class