AI-SPRINT defines a framework for developing AI applications in computing continua, enabling a finely-tuned tradeoff between performance and AI model accuracy, while providing security and privacy guarantees.
AI-SPRINT outcomes are:
- simplified programming models to reduce the steep learning curves in the development of AI software in computing continua;
- highly specialized building blocks for distributed training, privacy preservation and advanced machine learning models, to shorten time-to-market for AI applications;
- automated deployment and dynamic reconfiguration to decrease the cost of operating AI software.
Real-world scenarios are an integral part of AI-SPRINT as key to guiding requirements and development and validating results and bring to the development of three heterogeneous use cases (farming 4.0 maintenance & inspection, and personalized healthcare).