R
Razvan Andonie
Researcher at Central Washington University
Publications - 86
Citations - 835
Razvan Andonie is an academic researcher from Central Washington University. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 13, co-authored 85 publications receiving 650 citations. Previous affiliations of Razvan Andonie include Transylvania University & University of Washington.
Papers
More filters
Proceedings ArticleDOI
A class of loop self-scheduling for heterogeneous clusters
TL;DR: This work considers a class of Self-Scheduling schemes for parallel loops with independent iterations which have been applied to multiprocessor systems and presents tests that the distributed versions of these schemes maintain load balanced execution on heterogeneous systems.
Journal ArticleDOI
Extreme Data Mining: Inference from Small Datasets
TL;DR: This work discusses the meaning of "small" in the context of inferring from small datasets, and overviews computational intelligence solutions for this problem.
Journal ArticleDOI
Hyperparameter optimization in learning systems
TL;DR: This work presents an integrated view of methods used in hyperparameter optimization of learning systems, with an emphasis on computational complexity aspects, and creates the framework for a future separation between parameters and hyperparameters in adaptive P systems.
Proceedings ArticleDOI
Visualizing Transformers for NLP: A Brief Survey
TL;DR: In this article, a survey of Transformer architectures through visualizations is presented, focusing mainly on explaining Transformer architecture through visualisations, and a set of requirements for future Transformer visualization frameworks are proposed.
Journal ArticleDOI
Fuzzy ARTMAP with input relevances
TL;DR: The FAMR architecture is able to incrementally "grow" and to sequentially accommodate input-output sample pairs and the capability for mapping noisy functions when training data originates from multiple sources with known levels of noise is analyzed.