no code implementations • 12 Apr 2024 • Peter beim Graben
In my reconstruction, the convergence of the GAN algorithm during the reception of art, either music or fine, entails the harmony of the faculties and thereby a neural network analogue of subjective purposefulness, i. e., beauty.
no code implementations • 3 Apr 2024 • Peter beim Graben, Thomas Noll
Fitting Gaussian Mixture Models (GMM) to the Krumhansl-Kessler (KK) probe tone profiles for static attraction opens the possibility to investigate the underlying wave function as the stationary ground state of an anharmonic quantum oscillator with a schematic Hamiltonian involving a perturbation potential.
1 code implementation • 4 Feb 2023 • Jone Uria-Albizuri, Giovanni Sirio Carmantini, Peter beim Graben, Serafim Rodrigues
Our work could be of substantial importance for related regression studies of real-world measurements with neurosymbolic processors for avoiding confounding results that are dependant on a particular encoding and not intrinsic to the dynamics.
no code implementations • 24 Aug 2020 • Peter beim Graben, Markus Huber-Liebl, Peter Klimczak, Günther Wirsching
For speech assistive devices, the learning of machine-specific meanings of human utterances, i. e. the fossilization of conversational implicatures into conventionalized ones by trial and error through lexicalization appears to be sufficient.
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.
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)
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.
1 code implementation • 7 Sep 2016 • Giovanni Sirio Carmantini, Peter beim Graben, Mathieu Desroches, Serafim Rodrigues
We then show that the Goedelization of versatile shifts defines nonlinear dynamical automata, dynamical systems evolving on a vectorial space.
no code implementations • 4 Nov 2015 • Giovanni S Carmantini, Peter beim Graben, Mathieu Desroches, Serafim Rodrigues
We improve the results by Siegelmann & Sontag (1995) by providing a novel and parsimonious constructive mapping between Turing Machines and Recurrent Artificial Neural Networks, based on recent developments of Nonlinear Dynamical Automata.