WIP: adds lagrangian nn and simlple example

[manyfeatures]

PR adds Lagrangian NN implementation (#352)

Evident drawbacks:

• For Hessian and Jacobians all cross-derivatives are computed before extracting the useful ones
• Only one-point data has been tested
• Vectorization and batches are not tested
• No GPU support One sample training loss function:

More meaningful example is coming

[YichengDWu]

Related to https://github.com/JuliaDiff/FiniteDiff.jl/issues/147