GPUs and Deep Learning Help Brewers Improve Their Suds

A Pennsylvania start-up is using GPUs in the Amazon cloud to identify flaws, taints and contaminations to assist brewers with quality control. 24-year-old entrepreneur Jason Cohen and his 11-employee team, is using his companyʼs Gastrograph software that can now identify dozens of obscure beer styles — Vienna lagers, Irish dry stouts or Berliner Weissbiers — in seconds, rather than minutes.


The start-up is using GPUs for more than just classifying beers – they’re using them to create models that help analyze profiles generated by tasters against the more than 100,000 beer reviews his company has collected.

Without the parallel architecture of GPUs, for example,  it took Cohen’s team a long time to train deep neural networks with many layers, or random forest models with many trees. Cohen’s team now uses NVIDIA’s CUDA toolkit in R — such as gputools and gmatrix — to boost performance. Now model tuning only takes minutes to complete.

Read the entire blog on the NVIDIA corporate blog >>