Next Meetup

Knowledge Graph Convolutional Networks & Introducing Grakn
#### Knowledge Graph Convolutional Networks As humans we use our knowledge, our reasoning and our understanding of situational context to make accurate predictions about the world around us; machine learning doesn’t typically make use of any of this rich information. The ability to leverage highly interrelated data will yield a step-change in the quality and complexity of predictions that can be made for the same volume of data. We present Knowledge Graph Convolutional Networks: a method for performing machine learning over a Grakn Knowledge Graph, which captures micro-context and macro-context for any Concept within the graph. This methodology demonstrates how we can usably combine knowledge, learning and reasoning to build systems that start to look truly intelligent. Read more about KGCN: #### James Fletcher, MEng in Engineering Science from University of Oxford, Principal Scientist @Grakn Labs James is the Principal Scientist at Grakn, primarily working on educating the world on how to use a knowledge graph such as Grakn to build cognitive/intelligent systems. For this he is implementing examples as templates and ideas for how clients and community members can innovative in their own specific projects. With a background in Computer Vision, having co-founded his own startup in veterinary diagnostics, James's priority is to research the new kinds of intelligent system that are enabled by using Grakn as a knowledge graph There will be pizza, code, and most a certainly a good time! Timings: 18.30 - 19.00: Networking & Pizza 19.00 - 19.45: Knowledge Graph Convolutional Networks & Introducing Grakn 19.45 - 21.00: Networking & Drinks Venue: Royal Academy of Engineering 3 Carlton House Terrace, St.James's, SW1Y 5DG Please enter the Academy and ask for the ERA Foundation room for the pre-event networking. The talk will happen in the Qasimi north room.

Royal Academy of Engineering

3 Carlton House Terrace, St.James's, SW1Y 5DG · London

    Past Meetups (18)

    What we're about

    Intelligent/Cognitive Systems consume data that are too complex for current databases to handle. GRAKN.AI is a hyper-relational database that allows you to perform knowledge engineering to manage this complexity. Effectively, Grakn provides a Knowledge Base (aka. Knowledge Graph) as the core foundation of intelligent systems.

    Grakn provides an intelligent query language, Graql: Grakn’s reasoning (through OLTP) and analytics (through OLAP) query language, which is a much higher-level abstraction over traditional query languages. This allows intelligent systems to benefit from an intuitive language the provides an expressive schema for knowledge modelling, reasoning transactions for real-time inference, distributed algorithms for large-scale analytics, and optimisation of query execution. Grakn also provides the logical integrity of SQL, the scale of relationships of Graph databases, and the horizontal scalability of NoSQL.

    In this community, we discuss the underlying technology and applications of the Grakn hyper-relational database. We will also discuss the techniques of a new software engineering principle, Knowledge-Driven Development, that Grakn now enables. The group is for engineers to demonstrate their solutions and share the lessons they learnt, as well as business leaders to learn applications of Grakn in their business.

    Members (1,410)

    Photos (79)