Our Director of ML Architecture Lawrence Spracklen is speaking at Data Con LA 2021 virtually on September 18th, 4:45 – 5:25PM PT. He will be talking about sparse models and how they can provide performance advantages with no loss of accuracy.
Data Con LA is a three day conference featuring data and technology enthusiast. They cover a variety of topics such as data infrastructure and security, machine learning, emerging technologies etc. Check out their website for more information.
Abstract:
Sparse DNNs provide a powerful technique for delivering significant performance benefits and power savings without impacting the accuracy of your models. We present an introduction to sparse models, details on how to create and run sparse models, and guidance on how to ensure their robustness and fairness.
Lawrence Spracklen • VP of Machine Learning