Machine Learning is hard, but MLaaS makes it cheap and easy to add artificial intelligence to your apps!
Companies like Microsoft and Google have trained world-class models that allow us to implement AI with one line of code, making it easier than ever to implement Facial Recognition, Emotion Analysis, Optical Character Recognition and more!
Join me for a live-coding session to learn how to easily add Facial Recognition and Text Sentiment Analysis to your existing apps!
Target Audience: Developers
Prerequisites: Basic knowledge with REST APIs
I recently presented this talk at Microsoft's Build conference, focusing on Microsoft Cognitive Services and the video will be available shortly here: channel9.msdn.com/Events/Build/2018/THR2416/
Both Google and Microsoft offer similar MLaaS offerings and I'm happy to focus on both or just one if you prefer a Google-focused or a Microsoft-focused talk!
This talk shows how to build Machine Learning models at extreme scale and how to productionize the built models in mission-critical real time applications by leveraging open source components like TensorFlow and the Apache Kafka open source ecosystem in the public cloud - and why this is a great fit for machine learning at extreme scale. A live demo shows sensor analytics for predictive alerting in real time.
Target Audience: Architects, Developers, Project Leaders, Data Scientists
Prerequisites: Knowledge in data science and real time / streaming applications helpful, but not needed
This talk shows how to build a Machine Learning infrastructure for extreme scale and how to productionize the built models in mission-critical real time applications by leveraging open source components in the public cloud. The session discusses the relation between TensorFlow and the Apache Kafka ecosystem - and why this is a great fit for machine learning at extreme scale.
The Machine Learning architecture includes: Kafka Connect for continuous high-volume data ingestion into the public cloud, TensorFlow leveraging Deep Learning algorithms to build an analytic model on powerful GPUs, Kafka Streams for model deployment and inference in real time, and KSQL for real time analytics of predictions, alerts and model accuracy.
Sensor analytics for predictive alerting in real time is used as real-world example from Internet of Things scenarios. A live demo shows the out-of-the-box integration and dynamic scalability of these components on Google Cloud.
Key takeaways for the audience
• Learn how to build a Machine Learning infrastructure at extreme scale and how to productionize the built models in mission-critical real time applications
• Understand the benefits of a machine learning platform on the public cloud
• Learn about an extreme scale Machine Learning architecture around the Apache Kafka open source ecosystem including Kafka Connect, Kafka Streams and KSQL
• See a live demo for an Internet of Things use case: Sensor analytics for predictive alerting in real time