[Arm DevSummit - Session] Optimizing ML Models for Edge Devices Using Amazon SageMaker Neo

Abstract: Training a machine learning model in the cloud and deploying it on an edge device can sometimes feel like landing a booster on a barge but it doesn’t have to be rocket science. Join this session to learn how anyone can train, tune, and deploy models to cloud-connected devices with just a few APIs using Amazon SageMaker with Neo. Neo optimizes machine learning models to perform at up to twice the speed of the original framework with no loss in accuracy. We will train a TensorFlow model and a PyTorch model, compile them with Neo, and deploy them both on to the same runtime occupying barely 1 MB on an ARM Cortex-A device.  Presenters: Vin Sharma, Head of Engineering, Amazon SageMaker Neo Technical Level: Intermediate Target Audience: Software Developer Topics: #ArtificialIntelligence, #MachineLearning, #ArmDevSummit Type: Technical Session Conference Track: AI in the Real World: From Development to Deployment Air Date: 2020-10-08