← Cogitat in Media

Press release · 17 November 2026

Indivi acquires Imperial College’s Cogitat and its brain-decoding AI models

The acquisition equips Indivi with frontier AI capabilities that can support clinical trials for new treatments in Alzheimer's and related dementias.

Eight people standing together in front of a large brain-scan display at Imperial College London

Neurotech company Indivi, today announced it has acquired Cogitat, the Imperial College London spin-out developing cutting-edge deep learning models that decode cognitive function from EEG brain signals. The acquisition significantly strengthens Indivi’s deep tech capabilities and marks the firm's strategic expansion beyond life sciences, putting understanding of the human brain at the heart of its future.

Indivi will work with Cogitat’s world-class AI and scientific team to continue to develop the foundation model, which picks up fine detail in brain signals that other models may miss. Combined with Indivi’s leading edge in precision measurement, it will help detect the effects of experimental Alzheimer’s treatments, strengthening research and development across the life sciences. Looking ahead, the model could power new healthcare and consumer applications by turning EEG brain data into actionable insight.

Cogitat is a spin-out from Imperial College London, founded in one of the world’s leading machine learning labs. Its EEG foundation model, NeuroRVQ, powers brainwave decoders that are designed to work on anyone and on any device, with the goal of doing for the brain what large language models do for language. Cogitat’s machine learning capabilities won first place in the Benchmarks for EEG Transfer Learning (BEETL) competition at NeurIPS [1], one of the world’s most prestigious AI conferences, outperforming teams from academia and industry.

“This acquisition marks a new chapter for Indivi as a neuroscience-based AI company. The brain is the most complex organ in the body, and remains one of the hardest to understand and measure. Cogitat’s EEG foundation model changes that, decoding brain activity and revealing signals far closer to the underlying biology than ever before. That opens up exciting opportunities: initially the potential to provide drug developers earlier data on how new treatments are working for brain conditions, and, in the long-term, could inform the future development of next generation brain health technologies beyond life sciences.”

Guilhem Dupont, CEO and Founder of Indivi

“Every brain is unique and speaks its own language. We’ve built an advanced AI model that works across every brain’s unique language without individual training to identify subtle changes in brain activity that have not been easily identifiable before. This addresses one of neuroscience’s biggest translational gaps: the failure to detect early changes in brain biology that predict whether a treatment or product will actually work. With Indivi we have the opportunity to take our work to the next level, putting the model to work in the real-world, validating the technology and delivering true value.”

Allan Ponniah, CEO and Founder of Cogitat

Indivi’s next step: Foundation models informing treatment efficacy in Alzheimer's and related dementias

Indivi expects NeuroRVQ’s AI-driven approach to change how scientists and biopharma companies measure whether brain disease treatments, like Alzheimer's, are working. Over time, this could help sharpen clinical trials and speed effective treatments to market.

EEG offers a more direct window into brain activity, with the potential to detect changes before memory and thinking problems become clinically visible. Cogitat’s EEG foundation model, NeuroRVQ, learns the patterns of brain activity and preserves the fine, fast-changing detail that most models discard. Indivi aims to use this to pick up subtler signs of disease and treatment response than existing methods can detect.

NeuroRVQ will be presented at the 40th Annual Conference on Neural Information Processing Systems (NeurIPS, 6-12 December 2026) [2].

Sources

  1. Wei X et al. 2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets. Proceedings of Machine Learning Research (NeurIPS 2021 Competitions and Demonstrations Track), 2022. https://proceedings.mlr.press/v176/wei22a.html
  2. Barmpas K et al. NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models. NeurIPS 2026, Preprint: https://arxiv.org/abs/2510.13068

Media Contacts

Laura Moross (on behalf of Indivi and Cogitat): laura@lsmpr.co.uk

About Indivi

Indivi is a neurotech company headquartered in Basel, Switzerland, with offices in Córdoba, Spain and Boston, Massachusetts. Indivi combines precision measurement, advanced analytics, and scientific expertise to help biopharmaceutical sponsors design smaller early-phase trials and detect treatment effects with greater confidence.

Its multimodal platform currently includes smartphone-based motor and cognitive assessments, with work spanning Parkinson’s disease, neuromuscular diseases including facioscapulohumeral muscular dystrophy (FSHD), multiple sclerosis, and Alzheimer’s disease and related dementias.

Find out more at https://indivi.io/

About Cogitat

Cogitat is an Imperial College London spin-out developing AI that decodes brain activity from EEG. Its award-winning deep learning technology delivers precise brain activity decoding - from attention to movement control - across any EEG device.

The company is led by CEO and co-founder Allan Ponniah, alongside co-founders Dimitrios Adamos (CTO and Imperial Research Fellow) and Stefanos Zafeiriou (Chief Scientific Officer and Professor of Machine Learning at Imperial College London).