Nota AI and SiMa.ai have partnered to develop and commercialise on-device AI solutions for industrial environments. The collaboration focuses on optimising AI models for high-performance workloads.

The partnership combines Nota AI’s model compression technology with SiMa.ai’s machine learning system-on-chip (MLSoC) hardware. The companies intend to integrate Nota AI’s NetsPresso SDK with SiMa.ai’s Palette SDK to allow for the efficient deployment of AI models on edge devices. This integration is designed to achieve high inference performance while maintaining low power consumption.

“We look forward to working together with SiMa.ai to build on-device AI solutions that can be practically deployed in real-world industrial environments,” said Myung-su Chae, CEO of Nota AI. He stated that the collaboration will accelerate the expansion of AI optimisation into the physical AI market.

Nota AI’s NetsPresso platform can reduce AI model sizes by more than 90% while maintaining accuracy. This allows complex models to run on SiMa.ai’s ultra-efficient hardware. The companies also plan to deploy Nota AI’s generative AI-based video intelligence solution, NVA, for industrial monitoring and intelligent transportation systems.

Krishna Rangasayee, founder and CEO of SiMa.ai, said that software optimisation is essential for AI models to run reliably in physical environments. The companies stated they will also pursue joint business opportunities in the robotics and mobility sectors as part of the long-term collaboration.