On 11/16/2015 10:45 AM, Kevin Swingler wrote:
Different algorithms support varying degrees of human
most obvious examples are a decision tree (say, J48) which is easy to
visualise and understand and a MLP, which is very difficult to interpret
without further analysis.
Sorry for the SSF, but this remark makes me think of a paper I wrote a long time ago about
how to select a ML algorithm, which might be of interest for beginners here:
"Selecting Learning Algorithms for the Design of Virtual Players in Natural Resources
Management Platforms". Guillaume MULLER and Jaime S. SICHMAN. Proceedings of the
VIIIth Brazilian Symposium on Games and Digital Entertainment. Sociedade Brasileira de
Inteligencia Artificial. Rio de Janeiro, RJ Brazil. October, 8th-10th 2009
I'm sure it's not perfect (I was not a ML expert and I was specifically looking
for an algorithm able to manage sequences), but there are plenty of good references in the
KOTSIANTIS, S. 2007. Supervised machine learning: a review of classification techniques.
which is the inspiration for my own work...
Hope this can help
PS: I'm not working on this project anymore, but I'm always opened to
comments/corrections about this work!