5 papers
Dropout Neural Network Training Viewed from a Percolation Perspective
Finley Devlin, Jaron Sanders
In this work, we investigate the existence and effect of percolation in training deep Neural Networks (NNs) with dropout. Dropout methods are regularisation techniques for training…
Asymptotically optimal reinforcement learning in Block Markov Decision Processes
Thomas van Vuren, Fiona Sloothaak, Maarten G. Wolf +1
The curse of dimensionality renders Reinforcement Learning (RL) impractical in many real-world settings with exponentially large state and action spaces. Yet, many environments exh…
In situ fine-tuning of in silico trained Optical Neural Networks
Gianluca Kosmella, Ripalta Stabile, Jaron Sanders
Optical Neural Networks (ONNs) promise significant advantages over traditional electronic neural networks, including ultrafast computation, high bandwidth, and low energy consumpti…
Demonstration of effective UCB-based routing in skill-based queues on real-world data
Sanne van Kempen, Jaron Sanders, Fiona Sloothaak +1
This paper is about optimally controlling skill-based queueing systems such as data centers, cloud computing networks, and service systems. By means of a case study using a real-wo…
Learning payoffs while routing in skill-based queues
Sanne van Kempen, Jaron Sanders, Fiona Sloothaak +1
Motivated by applications in service systems, we consider queueing systems where each customer must be handled by a server with the right skill set. We focus on optimizing the rout…