Achieve up to 1.33 Times the Wide & Deep Recommender Performance by Selecting Amazon M6i Instances Featuring 3rd Gen Intel Xeon Scalable Processors

Description

Across Different Instance Sizes, M6i Instances Performed More Inference Operations per Second than M5n Instances with 2nd Gen Intel Xeon Scalable Processors

One application of deep learning inference is generating recommendations for shoppers visiting your website. As they browse, you collect data on the products that interest them. You can use this data, along with patterns from other visitors, to infer other products they might like and recommend them. To perform this data analysis in real time to boost your company’s sales, you can use deep learning workloads—specifically Wide & Deep recommendation engines.