Main optimisation algorithms used for training boron-doped silicon chips both in hardware and with surrogate models.

This package was created by the Brains team of the NanoElectronics research group at the University of Twente. It was designed and developed by:

• Unai Alegre-Ibarra, @ualegre (u.alegre@utwente.nl)
• Hans Christian Ruiz-Euler, @hcruiz (h.ruiz@utwente.nl)

With the contribution of:

• Bram van de Ven, @bbroo1 (b.vandeven@utwente.nl) : General improvements and testing of the different hardware drivers and devices.
• Michel P. de Jong @xX-Michel-Xx (m.p.dejong@utwente.nl): Testing of the package and identification of bugs.
• Michelangelo Barocci @micbar-21. The usage of multiple DNPUs simultaneously and the creation of an improved PCB for measuring DNPUs.
• Jochem Wildeboer @jtwild Nearest neighbour loss functions.
• Annefleur Uitzetter: The genetic algorithm from SkyNEt.
• Marcus Boon: @Mark-Boon: The on-chip gradient descent.

Some of the code present in this project was refactored from the skynet legacy project. The original contributions to the scripts, which are the base of this project, can be found at skynet, and the authorship remains of those people who collaborated in it. Using existing scripts from skynet, a whole new structure has been designed and developed to be used as a general purpose python library.