Tags give the ability to mark specific points in history as being important
  • VERSION_2019.4.1   Released v2019.4.1.
    • Major bug-fixes of version 2019.3.1
    • Made changes to facilitate Simulator functionality
  • VERSION_2019.3.1   Released v2019.3.1.

    Implemented training methods

    • Gradient descent
    • Mini-batch gradient descent
    • Barzilai-Borwein method
    • Levenberg-Marquardt method
    • Global particle swarm optimization
    • Training sequence

    Supported architectures

    • Feed-forward (FF)
    • Incomplete FF networks
    • Sets of FF networks with shared weights

    Applied functionality

    • Simple ODE/PDE solver

    Degree of parallelization

    • Sequential implementation