Authors:
Tom Gedeon
and
Anthony Oakden
Affiliation:
The Australian National University, Australia
Keyword(s):
Extreme Learning Machines, Cascade Correlation, Shallow Cascade, Simple Cascade, Full Cascade, Cascade Extreme Learning Machine, Cascade ELM.
Related
Ontology
Subjects/Areas/Topics:
Formal Methods
;
Neural Nets and Fuzzy Systems
;
Simulation and Modeling
Abstract:
We compare extreme learning machines with cascade correlation on a standard benchmark dataset for
comparing cascade networks along with another commonly used dataset. We introduce a number of hybrid
cascade extreme learning machine topologies ranging from simple shallow cascade ELM networks to full
cascade ELM networks. We found that the simplest cascade topology provided surprising benefit with a
cascade correlation style cascade for small extreme learning machine layers. Our full cascade ELM
architecture achieved high performance with even a single neuron per ELM cascade, suggesting that our
approach may have general utility, though further work needs to be done using more datasets. We suggest
extensions of our cascade ELM approach, with the use of network analysis, addition of noise, and
unfreezing of weights.