We present a size-aware type system for first-order shapely function definitions. Here, a function definition is called shapely when the size of the result is determined exactly...
Olha Shkaravska, Ron van Kesteren, Marko C. J. D. ...
Recently, sample complexity bounds have been derived for problems involving linear functions such as neural networks and support vector machines. In many of these theoretical stud...
— This paper studies the problem of stability analysis for neural networks (NNs) with a time-varying delay. The activation functions are assumed to be neither monotonic, nor diff...
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea ...
We propose an algorithm for function approximation that evolves a set of hierarchical piece-wise linear regressors. The algorithm, named HIRE-Lin, follows the iterative rule learn...