no code implementations • 1 May 2020 • Mogens Graf Plessen
Thereby, a sequence of labels is assigned for each time series.
no code implementations • 16 Dec 2019 • Mogens Graf Plessen
Benefits of proposed approach include simplicity, adaptability to a wide range of different shapes of time series, and in particular computational efficiency that make it suitable for big data.
no code implementations • 5 Jul 2018 • Mogens Graf Plessen
It is distinguished between 5 core aspects: system model, network architecture, training algorithm, training tasks selection and hardware/software implementation.
no code implementations • 29 Nov 2017 • Mogens Graf Plessen
Within the context of autonomous driving a model-based reinforcement learning algorithm is proposed for the design of neural network-parameterized controllers.