Had a great time attending @Geccoconf (virtually) this week. Thought I would dump some opinions/reflections into the twitter bit bucket before I forget them (thread)
1/ The organizers did an outstanding job of making this conference work well online. Talks on zoom, posters and social in gather.town. Sure, it's not as good as in person and time zones are a pain, but the low cost and accessibility are big positives.
2/ I was very impressed by the quality of the papers and talks. In the past there were times when some of the #machinelearning community would have scoffed at #evolutionarycomputation for being full of weird heuristics and crappy experimental standards.
3/ If anything, the situation is somewhat the opposite: #benchmarking has become a big focus in EC and people are talking about reproducibility and doing good experiments, while #deeplearning experiments sometimes leave a lot to be desired.
4/ EC seems to have embraced research directions combining with other disciplines - e.g. neuroevolution. This is great to see. It's a real melting pot of continuous and discrete theory, stats, ML, visualization, etc. This is when exciting things happen!
5/ Of course not everything in the field is perfect - we've still got the silly fish/whale/frog/whatever algorithm stuff which is not a good look.
6/ Onward and upward, @Geccoconf! Perhaps time to consider #openreview and revisit the oral/2nd class poster thing?
• • •
Missing some Tweet in this thread? You can try to
force a refresh
