Variational Autoencoders (VAEs) suffer from degenerated performance, when learning several successive tasks. This is caused by catastrophic forgetting. In order to address the knowledge loss, VAEs are using either Generative Replay (GR) mechanisms or Expanding Network Architectures (ENA). this paper we study forgetting behaviour of a joint GR and ENA methodology, deriving an upper bound on nega...

This paper reviews recent developments in our project that are focused on dynamic data-driven methods for efficient and reliable simulation based optimization, which may be suitable for a wide range of different application problems. The emphasis in this paper is on the coupling of parallel multiblock predictive models with optimization, the development of autonomic execution engines for distri...

This article estimates worker switching costs and how much the employer switching of experienced engineers responds to outside wage offers. I use data on engineers across Swedish private sector firms to estimate the relative importance of employer wage policies and switching costs in a dynamic programming, discrete choice model of employer choice. The differentiated firms are modeled in employe...