Machine Learning (ML) works by using powerful algorithms to discover patterns in data, and constructing complex mathematical models using these patterns. Once a model is built, you perform inference by applying data to the trained model to make predictions for your application. Building and training ML models requires massive computing resources so it is a natural fit for the cloud. But, inference takes a lot less computing power and is typically done in real-time when new data is available, so getting inference results with very low latency is important to making sure your applications can respond quickly to local events. AWS Greengrass ML inference gives you the best of both worlds. You use ML models that are built and trained in the cloud, and you deploy and run ML inference locally on connected devices. For example, autonomous cars need to identify road signs in real time; and drones need to recognize objects with or without network connectivity.
22. AWS DeepLens
HD video camera
Custom-designed
deep learning
inference engine
Micro-SD
Mini-HDMI
USB
USB
Reset
Audio out
Power
HD video camera
with on-board
compute optimized
for deep learning
Tutorials, examples,
demos, and pre-
built models
From unboxing
to first inference
in <10 minutes
Integrates with
Amazon SageMaker
and AWS Lambda
10
MIN
The world’s first deep learning-enabled video camera for developers
27. Problem
Nokia saw a need in industrial IoT to analyze
video streams at the edge and send the data
to remote centers only when anomalies are
detected.
Solution
Deploying AWS Greengrass on Nokia Multi-
access Edge Computing platform and
combining it with Nokia private mobile
network solutions. This joint solution makes
it possible for the oil industry to pair real-
time drilling data with production data
of nearby wells.
Impact
Due to the high cost of bandwidth being, this
solution enables Nokia to optimize the data
that is sent to other wells and to the cloud
based on rules and alerts set up on
the locally processed data.
28. Problem
Wärtsilä needed to accurately predict when the
marine engines they manufactured needed to
get serviced. Understanding and predicting the
service schedule is vital for Wärtsilä to increase
their service and parts revenue.
Solution
Accenture worked with AWS account SAs, AoD
SAs, and Salesforce SAs to architect an IoT
solution using Salesforce and AWS IoT Core to
collect data and build predictive models. The
solution they developed is scalable and
extensible beyond just this use case, as Wärtsilä
has 14,000 ships with 35,000 engines installed.
There are great possibilities for sensor-driven IoT
use cases.
Impact
The entire solution should result in an increase
in parts and service sales for Wärtsilä and higher
customer retention.