The spin-out has developed proprietary algorithms which allow neural networks to be trained on a fragmented or incomplete database
Cambridge, UK, 6 December 2017
Intellegens, a new company spun out of the University of Cambridge to develop and commercialise novel artificial intelligence (AI) software, 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 with a unique Artificial Intelligence (AI) toolset that can train deep neural networks from sparse or noisy data. The technique, created at the Cavendish Laboratory, is encapsulated in Intellegens first commercial product, Alchemite™. The innovative deep learning algorithms that Alchemite™ is based on can see correlations between all available parameters, both inputs and outputs, in fragmented, unstructured, corrupt or even noisy datasets. The result is models that can predict missing values, find errors and optimise target properties. Capable of working with data that is as little as 0.05% complete, Alchemite™ can unravel data problems that are not accessible to traditional deep learning approaches. Suitable for deployment across any kind of numeric dataset, Alchemite™ is delivering ground breaking solutions in drug discovery, advanced materials, patient analytics and predictive maintenance – enabling organisations to break through data analysis bottlenecks, reduce the amount of time and money spent on research, and support better, faster decision-making. For more information contact us here.