DataHour: Designing an end-to-end Neural Search Pipeline with Similarity Learning

Online 18-08-2022 07:00 PM to 18-08-2022 08:00 PM
  • 8839


  • Knowledge and Learning


DataHour Recording

About the DataHour:

The good old world of search engines had been dominated by keyword-based search for ages. But it has reached its limits. Neural embeddings allow us to explore completely new areas, including visual and audio search. Thanks to publicly available pretrained models, everybody can reuse a particular network for their tasks. And that no longer requires dozens of GPUs or labeling millions of data points. Similarity learning is a modern approach that lowers the data requirements while keeping great performance. 

In this DataHour, Kacper is going to describe the basics and present how to create an end-to-end pipeline using specialized tools.

Prerequisites:  Enthusiasm for learning Data Science and basic understanding Neural Networks.

Who is this DataHour for?

  • Students and professionals looking to expand their data science knowledge base.
  • Data Science and Engineering professionals who want to accelerate their career growth


Kacper Łukawski

Developer Advocate at Qdrant

Kacper Łukawski is a Developer Advocate at Qdrant - an open-source neural search engine. His broad experience is mostly related to data engineering, machine learning, and software design. He has been actively contributing to the discussion on Artificial Intelligence by conducting lectures and workshops locally and internationally. Recently he’s been focusing on similarity learning and vector search.

You can follow him on Linkedin, Twitter and Github.


Please register/login to participate in the contest

Please register to participate in the contest

Please register to participate in the contest



We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy.


We believe in making Analytics Vidhya the best experience possible for Data Science enthusiasts. Help us by providing valuable Feedback.