Abstract: "In this two part workshop series we will step through how you can leverage AI in your current Data Analytics Plane. This is an interactive session and we expect that you will be following along as we go, but don’t worry we have git repos and notebooks at the ready. All you need to bring is your laptop and your favourite training data sets if you prefer not to use the ones we provide.
Part I : expert-system-gpt
Writing good documentation and finding answers to internally sourced questions is tough so let's create our own in-house expert to help us out. We will create our own expert system by leveraging the power of an open source foundation model GPT-NeoX. We will walk through the complete end to end process from the experimentation in notebooks to productionisation and finally deployment as an API or Gradio application that can be used by anyone internally in a secure fashion for any number of applications. Along the way you will also learn how GPT models work and therefore both their capabilities and limitations.
Session Repository: https://github.com/ShawnKyzer/expert-system-gpt
Part II : synthetic-data-generator
We will create a machine learning pipeline to generate time series and other types of datasets using GAN(Generative Adversarial Networks) and LSTM models. We will go from our initial experimentation notebooks to writing production ready ML pipelines that you can deploy in your own cloud environment for use by your teams. Once you are done you will not have to rely on using production data in development pipelines again!
Session Repository: https://github.com/ShawnKyzer/synthetic-data-generator
Some familiarity is recommended but not required as I will explain each and give examples they can use directly to get started.
Bio: Shawn is passionate about harnessing the power of data strategy, engineering and analytics in order to help businesses uncover new opportunities. As an innovative technologist with over 15 years experience, Shawn removes technology as a barrier, and broadens the art of the possible for business and product leaders. His holistic view of technology and emphasis on developing and motivating strong engineering talent, with a focus on delivering outcomes whilst minimising outputs, is one of the characteristics which sets him apart from the crowd.
Shawn’s deep technical knowledge includes distributed computing, cloud architecture, data science, machine learning and engineering analytics platforms. He has years of experience working as a consultant practitioner for a variety of prestigious clients ranging from secret clearance level government organizations to Fortune 500 companies.
Shawn C. Kyzer
Principal Data Engineer | Thoughtworks (Spain)