CAMBRIDGE CATALYST Issue 05

TECH BYTES

INTELLEGENS TAKES FLIGHT

A Cambridge start-up has been selected for an accelerator programme run by aerospace powerhouse, Boeing. Intellegens, which uses its artificial intelligence toolset to train deep neural networks from sparse or noisy data, is going to be part of the ATI Boeing Accelerator programme. The programme is designed to support the growth of start-ups in the UK’s aerospace ecosystem to bolster the growth and competitiveness of the UK aerospace industry. Intellegens, along with nine other start-ups, were selected from 268 applicants.

Intellegens, a spin-out from Cambridge University, helps clients accelerate innovation by using its deep- learning solutions to extract valuable information from existing processes and data. The Alchemite platform is based on cutting-edge deep learning algorithms that can see correlations between all available parameters, both inputs and outputs, in fragmented, unstructured, corrupt or noisy data sets, even those that are as little as 0.05% complete. The generated models can predict missing values, find errors and optimise target properties with greater levels of

ABOVE CEO Ben Pellegrini (left) with co-founder Dr Gareth Conduit

accuracy than traditional approaches where complete data is needed. Dr Gareth Conduit, co-founder of Intellegens, explained: “Alchemite can unravel data problems that aren’t accessible to traditional deep- learning approaches, and is suitable for deployment across any kind of numeric data set. Our technology is capable of computationally designing and optimising processes for heat- resistant and lightweight alloys and can predict multiple material properties for a broad range of target criteria. We are enabling organisations to break through data analysis bottlenecks, reduce the amount of time and money spent on research, and support better, faster decision-making.” As part of the accelerator programme, Intellegens will receive a £100,000 equity investment from Boeing HorizonX Ventures, Boeing’s investment vehicle, as well as first-hand access to ATI, Boeing and GKN Aerospace strategists and technical experts.

Alchemite can unravel data problems that aren’t accessible to traditional deep-learning approaches, and is suitable for any kind of numeric data set"

ISSUE 05 31

cambridgecatalyst.co.uk

Powered by