Jason Bell, Senior Data Engineer

Jason Bell is a data engineer and startup founder based in Northern Ireland. He authored the book Machine Learning: Hands on for Developers and Technical Professionals. An in demand speaker and panelist, Jason has previously spoken at the Strata Data Conference in London on Kafka and AI technologies, the Digital DNA conference on AI and spends his spare time studying supply and demand pricing on different asset types (yes he does this for fun).



Talk Title:

Learning how to design automatically updating AI with Kafka and Deeplearning4j


With the increased development and adoption of streaming platforms, we now have a solid mechanism for collecting and processing data in a timely fashion. The growth and interest in machine learning and artificial intelligence has also given us refined prediction and decision making.

Jason Bell offers an overview of an automated self-learning knowledge system that uses Kafka and Deeplearning4j to accept data, apply training to a neural network, and output predictions. Jason covers the system design and the rationale behind it and the implications of using a streaming data with deep learning and artificial intelligence. Along the way, Jason explores the considerations that have to be made on how this application can continually learn, when manual intervention is required, and how to evaluate incremental learning. No programming knowledge is required

. Topics include:
- Planning the system
- Using Kafka Connect to store raw streaming data
- Defining a Deeplearning4j neural network
- Reapplying neural network training with new training data
- Making predictions