Weitere ähnliche Inhalte Ähnlich wie Introduction to Machine Learning on Mobile: Mobile Week SF (20) Mehr von Amazon Web Services (20) Introduction to Machine Learning on Mobile: Mobile Week SF1. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Introduction to Machine Learning
on Mobile
Dennis Hills
Mobile Developer Advocate
Pop-up Loft
2. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
What is AI?
Artificial Intelligence (AI) is a broad term for applying ANY technique that
enables computers to mimic human intelligence, using logic, if-then rules,
decision trees, and machine learning (including deep learning). – think
chatbots, robots, and KITT from Knight Rider!
Inventing entirely
new customer
experiences
Drones Voice driven
interactions
3. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
What is Machine Learning?
A subset of AI: Machine learning
(ML) is a set of methods that can
automatically detect patterns in data,
and then use the uncovered patterns
to predict future data, or to perform
other kinds of decision making under
uncertainty.
Personalized
recommendations
Fulfillment
automation and
inventory
management
4. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
More definitions…
Machine Learning is all about using data to answer
questions. First, data (e.g., images, text, or voice) is
provided along with answers (labels) to that data. Then
the computer (model) is trained on this data so it can
“learn” and later make predictions (aka inference) on
the mobile device.
5. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Important limitations for mobile
In general… mobile apps use pre-trained models to make
predictions. These models are first trained outside of the
app—typically in the cloud—and then brought into the
app to accomplish the task you desire.
6. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Why all the hype?!
Several developments in the world of ML
are creating an exciting playing field for
mobile developers:
7. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
What’s Changed?
Advances in neural networks (algorithms) have
dramatically improved accuracy in recognizing
images and speech. Accuracy rates matter. So,
what seemed like science fiction not so long ago is
here today.
1
8. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
What’s Changed?
Advances in cloud computing have greatly
reduced the time it takes to train these models. I’m
talking weeks to hours! That means fewer
resources, reduced capital expenses, and faster to
market.
2
9. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
What’s Changed?
There’s also been a flood of third-party API-driven
machine learning services hitting the market that
do a lot of the heavy lifting for you. Build your own
or let someone else do it.
3
10. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Three Types of Machine Learning
Supervised Learning
Unsupervised Learning
Reinforcement Learning
11. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Supervised Learning
Supervised learning is a system of all labeled
data and a predictive model. We use labeled data
to train a “model” and then use that “model” to make
predictions (inference) on new unlabeled data. The
trained model is the core of our discussion when it
comes to machine learning on a mobile device.
12. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Getting Started
So, we now understand machine learning, why it’s
being used, and what problems it can solve, but how
do I start playing with it as a mobile developer?
13. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
iOS => Core ML
Android =>
TensorFlow Lite
14. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Now, you may be asking…why not TensorFlow
Lite on Android and iOS?!?!
Answer: Use the best tool for the job
15. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Best of Both Worlds When it Comes to Prediction
The ML model is really the core of ML and you are
simply interfacing with the same trained model on the
device, but using the best framework for each platform.
16. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Imagine a little baby sitting between the two icons . . . that baby is the ML Model
they both have in common.
17. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Thank you
Get Started:
aws.amazon.com/mobile
Dennis Hills on Twitter: @dmennis