Abstract: 

Apply machine learning models to different engineering areas has been of particular interests for many data science practitioners and software engineers. As one of the mostly popular machine learning framework, TensorFlow and Keras have been widely used in many production environments for its robustness and scalability.

In this session, we will provide a tutorial on TensorFlow and Keras, and guide your through a series of hands-on examples ranging from basic MNIST dataset to time series processing for model building. We will also cover data input and output processing with TensorFlow, from processing simple CSV files to cloud data warehouse services such as Google Cloud BigQuery. As a bonus we will also cover the integration of TensorFlow with Apache Kafka, to illustrate the streaming data pipeline that is used broadly across the industry.

Session Outline
Module 1: Introduction of TensorFlow and Keras
- Model building with Keras in simple steps.
- Time-Series processing and LSTM models.
Module 2: Data pipeline in TensorFlow.
- Understanding the data pipeline.
- Columnar dataset processing.
Module 3: Deploy machine learning models in production
- Bridge TensorFlow and cloud data services.
- Streaming data in production with TensorFlow and Kafka.

Background Knowledge
A basic understanding of machine learning and python is needed.

Bio: 

Yong Tang, Ph.D., is Director of Engineering at Ivanti. He is a core contributor of many open-source projects in machine learning and cloud native areas. He is a maintainer and SIG I/O lead of the TensorFlow project, and received the Open Source Peer Bonus award from Google for his contributions to TensorFlow. He is also a maintainer of Docker/Moby, the widely used open-source container platform, and a core maintainer of CoreDNS, a Cloud Native Computing Foundation (CNCF) graduated project for service discovery.