(Lawrence Berkeley National Lab: Berkeley, CA) -- A team of scientists at Berkeley Lab has developed an unsupervised multiscale machine learning technique that can automatically and specifically capture biomedical events or concepts directly from raw data.

In many data-driven biomedical studies, the data limitations (e.g., limited data scale, limited data label, unbalanced data, and uncontrollable experimental factors) impose great challenges to scientific discovery, which can only be addressed with advanced machine learning techniques. This work is described in the article, “Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications,” published January 2017, in the IEEE Transactions on Pattern Analysis and Machine Intelligence journal. The work provides an effective and efficient way of learning and targeting sharable information so data can be used across domains. It also potentially removes limitations, especially for biomedical studies.

 …