Implementation and Optimisation in ACTS of algorithms exposed in TrackML challenge

Porting and Analysis of top solution algorithms from the TrackML challenge to ACTS framework. The algorithms include the combinatorial Mikado tracker, Cloudkitchen's Neural Network and DAG-based tracker and top-quarks' logistic regression and outlier density estimation algorithm. Added an example of running a PyTorch model in ACTS and testing genetic algorithms for optimization of the Mikado Tracker