The objective of our collaborative multi-partner project is to create an open-source Deep Learning framework called AIDGE for edge and embedded Artificial Intelligence (AI), built around an established European value chain. The framework is designed to support diverse application domains that function independently while serving a broad international community. It offers an integrated, full-stack workflow from Neural Network design and optimization to AI application development and hardware-level implementation with automated code generation for specific hardware targets. The platform aims to provide researchers and developers with a flexible environment to explore novel AI concepts, rapidly prototype solutions, and ensure strong alignment between academic research and industrial requirements. This paper summarizes the progress, outcomes, and milestones achieved up to the second year of this three-year project.

The goal of the NEUROKIT2E project is to create an open-source Deep Learning framework for edge and embedded AI built around an established European value chain. This framework, called AIDGE, supports a wide range of application areas that operate independently and serve a global user community. It provides easy and fast full-stack solutions from Neural Network design and optimization to AI application development all the way down to hardware implementations while enabling code generation for application-specific targets. This platform provides flexibility for academic users in the AI domain to explore and innovate while allowing them the possibility to prototype systems, ensuring their work aligns well with industrial needs. This paper presents the results and achievements of the first part of this three-year project, along with its roadmap and expected outcomes.

This paper describes a first prototype of a testbed System on chip (SoC) to design and evaluate different Neuromorphic Deep Neural Networks (NN) cores. The$1.25mm\times 1.25mm$SoC was fabricated in a 65nm CMOS technology and implements a system composed of an ARM based microprocessor, two memory banks of 32KB, a QSPI serial interface and two NN accelerators. The first one is a novel neuromorphic accelerator consisting of a$5\times 5$kernel Symmetrical Simplicial (SymSimp) core with a depthwise separable structure, which allows to efficiently implement multi-channel convolutional layers by breaking 3D kernels into 2D kernels. The second is a 3×3 conventional MAC engine to implement the fully connected layers. Experimental results show an energy efficiency of 0.49pJ/OP, which is competitive when compared to similar technology ICs, and extrapolated to the MobileNetworkV2 ImageNet represents a factor of 2 improvement with respect to NVIDIA Jetson Nano.