Author: Oliver Kirsebom - Lead Acoustic Data Analyst
Christmas came early this year for MERIDIAN's data analytics team at Dalhousie University. After successfully competing in NVIDIA's Accelerated Data Science Call for Proposals, the team last week received a refurbished Titan V graphical processing unit (GPU), which will support their efforts to train deep neural networks to detect and classify underwater sounds. The Titan V GPU, valued at around $3,000, is especially designed for high-performance computing and deep learning applications (as opposed to graphics and gaming uses), and will enable us to process underwater acoustic data much more efficiently and train Deep Learning models significantly faster. Indeed, Xuhui Liu, data analyst at MERIDIAN, is already using the new GPU for developing more efficient ways of training Deep Neural Networks on small samples of training data.