Machine Learning

The stage offers insightful and focused talks on the latest trends in computer programming. Participants will have the opportunity to delve deep into the vast universe of software development, gaining essential skills to tackle complex challenges and craft innovative solutions.

Hosting della sala

Roberto Digennaro
Roberto Digennaro
we-go srl
13 jun 12:50 - 13:30
40 min
Let's demystify Gen AI and see how we can apply it to fun, approachable solutions, with a magical twist. We'll first explore how vector embeddings and LLMs work, before we set off to build our search solution (with a live demo). Using the Elastic Python clients we first create indexes for Harry Potter characters, and film subtitles. We can import compatible 3rd party LLMs through an enriching pipeline; allowing us to add sentiment analysis and embeddings to our text. We’ll build a semantic search engine that can browse the books better than the ultimate fan.
13 jun 14:20 - 15:00
40 min
Vector databases are transforming how we handle data, allowing us to search through text, images, and audio by converting them into vectors. Today, we'll dive into the basics of this exciting technology and discuss its potential to revolutionize our next-generation AI applications. We'll examine typical uses for these databases and the essential tools
developers need. Plus, we'll zoom in on the advanced capabilities of vector search and semantic caching in Java, showcasing these through a live demo with Redis libraries. Get ready to see how these powerful tools can change the game!
13 jun 17:00 - 17:40
40 min
Language Models have witnessed remarkable advancements across diverse domains, continually scaling in size and training on increasingly expansive datasets. This progression has bestowed upon them the remarkable ability to swiftly adapt to novel tasks with minimal training data. However, the journey of training models comprising tens to hundreds of billions of parameters on vast datasets is anything but straightforward. This presentation is designed to offer comprehensive insights into the intricacies of training and deploying the most expansive neural networks
13 jun 18:00 - 18:40
40 min
LLMs are the product of Industry 4.0 that has most influenced the current advancement of GenAI and ignited our imagination with endless application possibilities. In this talk, we will take a step back in time and look at their evolution, from pre-deep learning models to the current ones based on Transformer architecture. Finally, we will try to build a Large Language Model from (almost) scratch and discuss the difference between pre-training and fine-tuning, as well as their advantages and disadvantages.