Now that I have the opportunity, let me #introduce our quality-diversity #compchem algorithm to Mastadon. It's based on @janhjensen 's generative algorithm. We avoid stagnation issues, and illuminates opportunities across chemical space, and outperforms #deeplearning approaches!
Code: https://github.com/Jonas-Verhellen/Argenomic
Paper: https://pubs.rsc.org/en/content/articlelanding/2020/sc/d0sc03544k
+bonifartius 𒂼𒄄
@jverhell really nice, _especially_ because it isn't just a statistical model nobody understands (aka. deep learning) but a sound stochastic algorithm. is the implementation parallelized like described in the paper?
Follow
@bonifartius @janhjensen Yes, the fitness evaluation and description calculations are parallelised.
@jverhell nice! i think there is much to gain with specialized parallel algorithms instead of using parallelism for unspecific deep learning models.
@janhjensen