Join us for an exciting evening of networking and knowledge-sharing at the Graph Database Sydney Meetup on Nov 16th! Whether you’re a seasoned graph database enthusiast or just starting your journey into the world of connected data, this event is the perfect opportunity to connect with like-minded professionals, share insights, and explore the latest advancements in graph database technology.
During this meetup, we’ll delve into the power and versatility of graph databases and their applications across various industries. We’ll feature engaging talks, hands-on demonstrations, and interactive discussions, all aimed at deepening your understanding and igniting your curiosity about the potential of graph databases.
Venue: Microsoft Reactor Sydney, lvl 10/11 York St, Sydney, NSW 2000, Australia
The agenda of the evening would be:
– 5pm: doors open
– 5.30pm: announcements and welcome
– 5.40pm: 1st Talk
– 6.10pm: 2nd Talk
– 6:40pm: Networking
– 7.10pm: doors close
Speakers:
? Payam Mokhtarian, MLnet and Neo4j partner
Talk: Vector Search in Knowledge Graph to Enhance Generative AI Responses
Summary:
Generative AI models represent a paradigm shift in artificial intelligence. By learning patterns from vast datasets, these models can synthesise strikingly human-like creative output. But a key enabler behind generative AI’s remarkable capabilities is often overlooked; the capability of vector retrieval or vector search. This capability optimised for storing and retrieving vector representations of data, are central to successfully deploying generative AI models in production applications.Neo4j has recently introduced native Vector Search feature. Vector search provides a simple approach for quickly finding contextually related information and, in turn, helps to achieve richer insights from generative AI applications by understanding the meaning behind words rather than matching keywords.Vector search, combined with knowledge graphs, is a critical capability for grounding large language models (LLMs) to improve the accuracy of responses. In this talk, we explore how grounding LLMs with a Neo4j knowledge graph and vector search can improve accuracy, context, and explainability by bringing factual responses (explicit) and contextually relevant (implicit) responses to the LLM.
Bio: Payam is a seasoned expert in machine learning and AI, with a PhD in Machine Learning and over a decade of industry experience. Having worked in telecommunications, digital native companies, financial services and insurance, gaming, and cyber security, Payam possesses a diverse background. Throughout the past decade, Payam has been instrumental in helping organisations establish data science functions and scalable machine learning practices. More recently, he has been working on leveraging generative AI capabilities into enterprise readiness solutions to empower organisations to harness knowledge graphs for generative AI insights and recommendations that are more accurate, transparent, and explainable.
? Dr. Shameek Ghosh, Co-founder, Medius Health
Talk: Simulating Synthetic Data using Domain-specific Knowledge Graphs
Summary:
Depending on various business cases with respect to AI models, current practise in supervised learning often lead to key technical requirements such as large-scale training data acquisition, diversity of data points (for removing any bias), and aspects of customer data privacy. In this talk, we discuss synthetic simulation methods to generate training data using graphs and present examples.
Bio: Shameek Ghosh is Co-Founder of Medius Health. He obtained his PhD in Machine Learning at the University of Technology Sydney (UTS), where he developed novel sequential mining algorithms to extract interesting patterns from large scale electronic healthcare records to predict acute hypotension and septic shock events. Previously, his research had collaborations with MIT USA, NUS Singapore, and the NSW government, culminating into more than 30+ premier research publications (within large-scale graphs) and 2+ patents in machine learning. As Co-Founder in Medius Health, Shameek is spearheading the platform capability in artificial intelligence and leading the transformation, delivery, and deployment of pre-built AI models and data science solutions.
Interested to speak at this or future meetups? Fill this form:
https://dev.neo4j.com/submit-your-talk
Don’t miss out on this valuable opportunity to expand your graph database knowledge, make meaningful connections, and be part of the vibrant Sydney graph database community. Register now to secure your spot and join us on Nov 16th for an evening of discovery and inspiration!
We look forward to welcoming you to the Graph Database Sydney Meetup!
