Whether it's connected cars, smart home devices, or industrial applications, IoT applications are rapidly becoming more intelligent. Edge computing is helping lead this transformation as IoT devices not only collect and transmit data, but also perform predictive analytics and respond to local events, even without cloud connectivity. In this session, learn about ML inference at the edge, why it matters, and how to use it to build intelligent IoT applications. Through customer use cases, we demonstrate how to use AWS Greengrass to locate cloud-trained ML models, deploy them to your AWS Greengrass devices, enable access to on-device computing power, and apply the models to locally generated data without connection to the cloud.