Offered in partnership with Dell Technologies . This session introduces embedding models as a core component of modern m achine learning systems for clustering\, ranking\, and large-scale informa tion retrieval. It explains how embeddings are trained\, covering represen tation learning theory\, contrastive and metric-learning losses\, and data preparation strategies that influence embedding quality. An EmbeddingGemm a‑style code walkthrough illustrates dataset construction\, pairing\, an d negative sampling\, and connects training choices to retrieval performan ce using a real-world agentic search application at Dell.
Level of D ifficulty: Beginner to Intermediate
SUMMARY:Finetuning Your Embedded Model for Better Search: Learning from Age ntic Search at Dell URL;VALUE=URI:https://events.teams.microsoft.com/event/6c98649b-f99f-49dc-a ddf-b3d81c724328@2fff08c9-91d4-4fc8-bbdd-dd59b7414ddb END:VEVENT END:VCALENDAR