2 papers
q-bio.GN2018
Towards the Latent Transcriptome
Assya Trofimov, Francis Dutil, Claude Perreault +3
In this work we propose a method to compute continuous embeddings for kmers from raw RNA-seq data, without the need for alignment to a reference genome. The approach uses an RNN to…
stat.ML2018
Holographic Neural Architectures
Tariq Daouda, Jeremie Zumer, Claude Perreault +1
Representation learning is at the heart of what makes deep learning effective. In this work, we introduce a new framework for representation learning that we call "Holographic Neur…