ODSC Europe | June 14-15th, 2023 | In-person and Virtual
Vector Search
Learn the latest models, advancements, and trends from the top practitioners behind one of the field's hottest topics
FOCUS AREA OVERVIEW
Complex data such as text, documents, video, and images,, abound in many organizations but can be difficult to search, and in turn, utilize in products or services. Machine Learning can provide a far more helpful representation of complex data by transforming it into vector embeddings that describe complex data objects as numeric values at very high dimensions. These vector embeddings can be indexed and stored in vector databases for quick retrieval and similarity search, Vector databases are very good at vector search (similarity search). Vector search enables users to describe what they want to find without having to know which keywords or metadata classifications are attributed to the stored objects. Use cases for vector search include semantic search, recommendation systems, ranking, and similarity search for text, audio, images, video, and other types of unstructured data.
TOPICS YOU'LL LEARN
Vector Search
Vector Embeddings
Recommendation Systems
Question Answering
Vector Databases
Semantic Search
Data Classification
Multimodal Search
Confirmed Speakers
Laura Ham
Laura is a ML Product Researcher at SeMI Technologies, the company behind the open-source vector search engine Weaviate. She researches new machine learning features for Weaviate and works on everything UX/DX related to Weaviate. For example, she is responsible for the GraphQL API design. She is in close contact with our open source community. Additionally, she likes to solve custom use cases with Weaviate, and introduces Weaviate to other people by means of Meetups, talks and presentations.
Tuana Çelik
Tuana is a Developer Advocate at deepset. She works on improving the developer experience and adoption of deepset’s Open Source NLP framework: Haystack. Originally from Istanbul, she moved to the UK in 2014 where she obtained a Master’s degree in Computer Science from the University of Bristol (in 2018). She initially started her career as a Software Engineer but then decided to become more involved with open source communities and educating people. This led her to developer relations. She worked as a developer advocate at Cumul.io before moving to deepset in 2022.
Semantic Search in NLP – How to Build Question Answering with Haystack(Talk)
Connor Shorten, PhD
Connor Shorten is a Research Scientist at Weaviate, an Open-Source Vector Search Database. Connor has had a role in the development of Ref2Vec, Hybrid Search, Generative Search, Weaviate’s Pipe API, and Re-Ranking. Connor has also hosted 34 episodes of the Weaviate podcast featuring guests from OpenAI, Cohere, You.com, MosaicML, Jina AI, Deepset, Neural Magic and many others! Connor also co-hosts Weaviate meetups in Boston and New York City! Prior to Weaviate, Connor has earned a Ph.D. in Computer Science from Florida Atlantic University. Connor’s Ph.D. was primarily focusing on Data Augmentation in Deep Learning and Applications of Deep Learning for COVID-19. Connor’s publication “A survey on image data augmentation in deep learning” has achieved over 5,000 citations.
Building Recommendation Systems(Workshop)
Confirmed Talks
An Introduction to Vector Databases and Vector Search
In machine learning – like recommendation tools or data classification – data is often represented as high-dimensional vectors. These vectors are stored in so-called vector databases. Vector databases are the backbone of ML deployments in industry, they are designed and optimized to run search, ranking and recommendation algorithms.
If you are a data scientist or a data/software engineer join Laura to learn how to run your favorite ML models with a vector database like Weaviate. But also to learn about other features like semantic search, question answering, data classification, named entity recognition, and multimodal search, that you should expect from a Vector Database.
Finally, Vector search will be illustrated with live demos of a real use case! After this session, you will know when and how to use Vector Search with various ML models.
Semantic Search in NLP – How to Build Question Answering with Haystack
With the development of Transformer-based language models, NLP has had a leap in research and techniques in the last few years. These language models enable different tasks such as Question Answering, summarisation, translation, retrieval and so on. These, combined with vector optimized databases and the development of Open Source frameworks such as Haystack have made it possible for us to create NLP powered applications to a quality that was previously not possible. This talk will cover an intro to NLP and Question Answering, followed by an example on how to build a Question Answering pipeline with Haystack.
Vector Search for Data Scientists
Finding metrics that describe performance can unlock valuable insights in the field of Data Science. It can be helpful to visualize the distribution of these metrics and to understand how segments of metrics vary with each other. It is needed here to define categories such as age or gender that can divide the data, which is a limitation of segmenting analytics. Vector Search uses semantics to analyze data, and does not have the limitation of requiring symbolic tags. In this talk, you will learn how to use Vector Search as a Data Scientist. By means of real Youtube and Twitter data, you’ll see how easy it is to utilize this yourself with the Vector Search engine Weaviate
Why Attend?
Immerse yourself in talks, tutorials, and workshops on Machine Learning and Deep Learning tools, topics, models and advanced trends
Expand your network and connect with like-minded attendees to discover how Machine Learning and Deep Learning knowledge can transform not only your data models but also your business and career
Meet and connect with the core contributors and top practitioners in the expanding and exciting fields of Machine Learning and Deep Learning
Learn how the rapid rise of intelligent machines is revolutionizing how we make sense of data in the real world and its coming impact on the domains of business, society, healthcare, finance, manufacturing, and more
ODSC EUROPE Hybrid Conference 2023 | June 14-15th
Register & Save 75%ODSC Newsletter
Stay current with the latest news and updates in open source data science. In addition, we’ll inform you about our many upcoming Virtual and in person events in Boston, NYC, Sao Paulo, San Francisco, and London. And keep a lookout for special discount codes, only available to our newsletter subscribers!