Google Deepmind. For the VisualisingAI series, we translated two concepts in the evolving AI field—quantum computing and multimodality training—into visuals that stay close to the tech.

Google DeepMind’s Visualising AI initiative aims to create more diverse and accessible representations of AI by commissioning designers and artists from around the world to create new visual representations of topical AI concepts. They invited us to interpret two themes particularly relevant within the field of AI today: Quantum Computing and Multimodality Training. While given free rein on content and style, the Google Deepmind team proposed that we move away from purely abstract and poetic representations, towards the more literal and explanatory. We designed and produced a short animation and a selection of stills for each topic.

Apart from wanting to make both topics more relatable or accessible to a broader audience, we also considered a need voiced by the data scientists and engineers who work with these complex materials on a daily basis—including those we work with at BB and spoke to at Google DeepMind. By borrowing from the diagrammatic language often reserved for scientific and academic papers and merging it with a more evocative graphic language, our two visualisations aim to balance a meaningful level of technical complexity with accessible visual storytelling. Both visualisations are free to download at Unsplash and Pexels.

• Nikita Iziev (graphic design support, motion design)
• Vincenzo Marchese Ragona (graphic design support, motion design)
• Zelig (sound)