Intellegens has received funding from Cambridge Enterprise and local angel investor Graham Snudden.
The spin-out has developed proprietary algorithms which allow neural networks to be trained on a fragmented or incomplete database. Intellegens has already successfully deployed its code in two diverse applications: drug discovery and material design. where it has significantly cut customers’ costs by reducing the number of experiments thereby shortening development cycles and offering accelerated time-to-market.
The company was founded by Dr Gareth Conduit, a Royal Society Fellow at the Cavendish Laboratory, and Ben Pellegrini, an expert in big data and cloud-based platforms. The Intellegens approach can be applied to many other data domains. Current opportunities include health, autonomous cars and retail. To enable wider uptake of this approach, Intellegens is developing an online portal with additional funding from Innovate UK.
Dr Gareth Conduit, CTO and co-founder of Intellegens, said: “This new approach to applying AI to incomplete databases enables us to analyse significantly more data than traditional AI approaches, and to develop models that would otherwise be impossible. The approach is particularly relevant to experimental data where we can combine a small number of well-characterised records—typically created empirically at significant expense—with big fragmented databases, enabling us to infer high-value information. Having gained commercial validation with research partners in fields as diverse as, aero engines, semi-conductor and battery technology and oil and gas, we’re very excited about the broad range of commercial opportunities available”.
Elaine Loukes, Investment Manager at Cambridge Enterprise Seed Funds, said: “The Intellegens approach has already delivered impressive results, and we believe that it could provide compelling benefits in many other AI applications”
Intellegens is a spin-out from the University of Cambridge that has developed a unique Artificial Intelligence (AI) method for training neural networks from incomplete data. The technique, developed in the Department of Physics, has been applied to drug discovery and material design but as the technique is generic it can be applied to many domains where there is big, incomplete data. For more information, please visit www.Intellegens.ai or contact us at email@example.com
About Cambridge Enterprise Ltd
A wholly owned subsidiary of the University of Cambridge, Cambridge Enterprise is responsible for the commercialisation of University intellectual property. It provides access to early stage capital through the Cambridge Enterprise Seed Funds, University of Cambridge Enterprise Funds and Cambridge Enterprise Venture Partners, and offers business planning, mentoring and related programmes. Activities include management and licensing of intellectual property and patents, proof of concept funding and support for University staff and research groups wishing to provide expert advice or facilities to public and private sector organisations. For more information, please visit www.enterprise.cam.ac.uk or follow us on Twitter at @UCamEnterprise