Reinforcement learning of minimalist grammars

no code implementations • 30 Apr 2020 • Peter beim Graben, Ronald Römer, Werner Meyer, Markus Huber, Matthias Wolff

In order to develop proper cognitive information and communication technologies, simple slot-filling should be replaced by utterance meaning transducers (UMT) that are based on semantic parsers and a mental lexicon, comprising syntactic, phonetic and semantic features of the language under consideration.

reinforcement-learning Reinforcement Learning (RL) +2

Vector symbolic architectures for context-free grammars

no code implementations • 11 Mar 2020 • Peter beim Graben, Markus Huber, Werner Meyer, Ronald Römer, Matthias Wolff

Our approach could leverage the development of VSA for explainable artificial intelligence (XAI) by means of hyperdimensional deep neural computation.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Reinforcement Learning of Minimalist Numeral Grammars

no code implementations • 11 Jun 2019 • Peter beim Graben, Ronald Römer, Werner Meyer, Markus Huber, Matthias Wolff

In order to develop proper cognitive information and communication technologies, simple slot-filling should be replaced by utterance meaning transducers (UMT) that are based on semantic parsers and a \emph{mental lexicon}, comprising syntactic, phonetic and semantic features of the language under consideration.

reinforcement-learning Reinforcement Learning (RL) +2

Driver Identification Using Automobile Sensor Data from a Single Turn

no code implementations • 9 Jun 2017 • David Hallac, Abhijit Sharang, Rainer Stahlmann, Andreas Lamprecht, Markus Huber, Martin Roehder, Rok Sosic, Jure Leskovec

In this paper, we propose a method to predict, from sensor data collected at a single turn, the identity of a driver out of a given set of individuals.

Driver Identification Navigate +2