Comparision Of Adversarial And Non-Adversarial LSTM Music Generative Models

Autor: Mots'oehli, Moseli, Bosman, Anna Sergeevna, De Villiers, Johan Pieter

Algorithmic music composition is a way of composing musical pieces with minimal to no human intervention. While recurrent neural networks are traditionally applied to many sequence-to-sequence prediction tasks, including successful implementations of

Externí odkaz: http://arxiv.org/abs/2211.00731

Blind multi-user cancellation using the constant modulus algorithm

Autor: De Villiers, Johan Pieter

Please read the abstract in the section 00front of this document
Dissertation (M Eng (Electronic Engineering))--University of Pretoria, 2006.
Electrical, Electronic and Computer Engineering
unrestricted

Externí odkaz: http://hdl.handle.net/2263/28080
http://upetd.up.ac.za/thesis/available/etd-09212005-161002/

Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction

Autor: Dabrowski, Joel Janek, de Villiers, Johan Pieter, Rahman, Ashfaqur, Beyers, Conrad

Publikováno v: In: Gedeon T., Wong K., Lee M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham

The time it takes for a classifier to make an accurate prediction can be crucial in many behaviour recognition problems. For example, an autonomous vehicle should detect hazardous pedestrian behaviour early enough for it to take appropriate measures.

Externí odkaz: http://arxiv.org/abs/2002.11226

Naïve Bayes switching linear dynamical system: A model for dynamic system modelling, classification, and information fusion

Autor: Dabrowski, Joel Janek, de Villiers, Johan Pieter, Beyers, Conrad

Publikováno v: In Information Fusion July 2018 42:75-101

Systemic banking crisis early warning systems using dynamic Bayesian networks

Autor: Dabrowski, Joel Janek, Beyers, Conrad, de Villiers, Johan Pieter

Publikováno v: In Expert Systems With Applications 15 November 2016 62:225-242