Deep learning is a rapidly emerging field that gained a lot of attention in the context of computer vision. Deep learning involves the use of complex, multi-level “deep” neural networks to create systems that can perform feature detection from massive amounts of unlabeled training data. For example, voice recognition (speech to text) in mobile devices today is accomplished via deep learning networks. It is also the technology behind most image search engines and is at the cutting edge of current research, both in academia and the industry.
Today, the availability of training data and powerful and efficient computing capabilities provided by state of the art hardware platforms, have made the mainstreaming of deep learning possible.
As part of the prestigious EU-funded project 3D-MASSOMICS, SagivTech, together with SCiLS, UoB and EMBL, conducted research on the application of deep learning to MALDI images where the focus was for the use case of spectra selection.