Résumé
With the impressive success of deep learning, a recent trend is moving towards neuromorphic mixed-signal approaches to improve energy efficiency. However, the process of building, training, and evaluating mixed-signal neural models is slow and laborious. In this paper, we introduce an open-source framework, called EBANA, that provides a unified, modularized, and extensible infrastructure for building and validating analog neural networks (ANNs). It already includes the most common building blocks and maintains sufficient modularity and extensibility to easily incorporate new concepts. It uses Python as interface language with a syntax similar to Keras, while hiding the complexity of the underlying analog simulations. These features make EBANA suitable for researchers and practitioners to experiment with different design topologies and explore the various tradeoffs that exist in the design space.