Willem Meints
Chief AI Architect/Microsoft AI MVP
Actions
Willem Meints is Chief AI Architect for Info Support and Microsoft AI MVP responsible many machine-learning and AI projects at Info Support and Aigency.
Links
Awards
Building secure LLM applications on Azure: Here's what you should know
Building an intelligent chat application with GPT-4 is quite fun. However, it’s also dangerous because large language models have a unique attack surface that you must deal with. Hackers can quite easily steal information from you or abuse the language model.
In this session, you’ll learn how to deploy and protect an application on Azure that uses Azure OpenAI. You’ll learn how to set up a good process, tools to discover and mitigate risks, and how to implement countermeasures in Azure to protect against hackers who want to abuse your LLM application.
MLOps from the trenches: Building a computer vision solution to recognize shipping containers
We made a computer vision solution for a client that allows dock workers to quickly scan codes from shipping containers into an inspection app on their mobile phones so they can inspect the freight contained in the shipping containers. What sounded like an easy OCR project turned out to be quite an undertaking. We learned a ton from this project. For example that building a deep learning model can be quite a challenge especially when ready-made models turn out not to work for your case.
In this session, we’ll talk you through our approach and the lessons we learned. We’ll cover the following topics:
- How we made an MLOps environment on Azure without spending too much.
- How we handled a dataset with 5.3 million samples and how that broke our environment.
- How we deployed our model to Android and IOS so it can use the model without an internet connection.
- How we’re using A/B testing on Android devices to find out which model is the best.
If you’re interested in learning about MLOps outside the lab then this is certainly going to be entertaining.
Building a chat assistent with Azure OpenAI service
You’ve probably used ChatGPT or Github copilot in your work at least once or maybe you’re using it on a daily basis and maybe you’re wondering how you can build something like that yourself. This is the session for you. I’ll show you how we made our own ChatGPT instance at Info Support and connected it to our internal knowledge base. We’ll cover how to write a good system prompt, how to structure the conversation, and how to connect your own data sources. Finally, we’ll talk a little bit about using the chat API for other things than chat.
Exploring the Frontiers of Generative AI: A Dynamic Panel Discussion
This panel discussion delves into the captivating realm of generative AI, exploring the latest breakthroughs, challenges, and applications.
The conversation concludes with insights into the future of generative AI and responsible harnessing of its potential, providing a captivating and concise exploration for researchers, practitioners, and enthusiasts alike.
Exploring Vector Databases: A Comprehensive Guide to Setup, Usage, and Use Cases
Vector databases are a new invention that few developers have worked with before. It's a database but quite different from your average relational database. In this session, we'll take a deep dive into vector databases and how to set one up and use it from your C# code. We'll also look at some exciting use cases where we've used vector databases. Finally, we'll show you what we learned using a vector database.
Techorama Netherlands 2023 Sessionize Event
Global AI Generate Sessionize Event
Willem Meints
Chief AI Architect/Microsoft AI MVP
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top