30 citations
- University of IowaUS7 papers
- Nokia (Finland)FI3 papers
- Berlin Institute of Health at Charité - Universitätsmedizin BerlinDE2 papers
- Seoul National UniversityKR2 papers
- University of CopenhagenDK2 papers
- Aalto UniversityFI1 paper
- Birmingham City UniversityGB1 paper
- Cégep André LaurendeauCA1 paper
- Centre for Arctic Gas Hydrate, Environment and ClimateNO1 paper
- Cornell TechUS1 paper
- Cornell UniversityUS1 paper
- ETH ZurichCH1 paper
6 papers · 2 filters
Mislabel Detection of Finnish Publication Ranks
Anton Akusok, Mirka Saarela, Tommi Kärkkäinen +2
The paper proposes to analyze a data set of Finnish ranks of academic publication channels with Extreme Learning Machine (ELM). The purpose is to introduce and test recently propos…
Per-sample Prediction Intervals for Extreme Learning Machines
Anton Akusok, Yoan Miche, Kaj-Mikael Björk +1
Prediction intervals in supervised Machine Learning bound the region where the true outputs of new samples may fall. They are necessary in the task of separating reliable predictio…
Extreme Learning Tree
Anton Akusok, Emil Eirola, Kaj-Mikael Björk +1
The paper proposes a new variant of a decision tree, called an Extreme Learning Tree. It consists of an extremely random tree with non-linear data transformation, and a linear obse…
Spiking Networks for Improved Cognitive Abilities of Edge Computing Devices
Anton Akusok, Kaj-Mikael Björk, Leonardo Espinosa Leal +3
This concept paper highlights a recently opened opportunity for large scale analytical algorithms to be trained directly on edge devices. Such approach is a response to the arising…
Incremental ELMVIS for unsupervised learning
Anton Akusok, Emil Eirola, Yoan Miche +5
An incremental version of the ELMVIS+ method is proposed in this paper. It iteratively selects a few best fitting data samples from a large pool, and adds them to the model. The me…
Comparison of Classification Methods for Very High-Dimensional Data in Sparse Random Projection Representation
Anton Akusok, Emil Eirola
The big data trend has inspired feature-driven learning tasks, which cannot be handled by conventional machine learning models. Unstructured data produces very large binary matrice…