Re:Keras-based molecular autoencoder
by dkural on Monday October 24, 2016 @10:13PM
(#12784719)
What kind of genomic data out of curiosity?
[ Parent
| on HN ]
Is that actually working? I tried rolling my own neural nets and running genomic data through them and instantly realized the problem was low N, high autocorrelation in the data. Bayesian forests seem like a better choice, but that's me.
Re:Keras-based molecular autoencoder
by alextheparrot on Tuesday October 25, 2016 @12:27AM
(#12785292)
There have been some recent papers in subsets of genomics with a bit more data (Transcription factor binding, for example [1]). You're correct though, definitely depends on your problem.
[1] https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4908339/pdf/btw...