NengoDL: Combining deep learning and neuromorphic modelling methods
This provides a unified tool for researchers in computational neuroscience and AI to bridge neuromorphic and deep learning approaches, though it is incremental as it builds on existing methods.
The authors tackled the integration of neuromorphic modeling and deep learning by developing NengoDL, a software framework that enables users to build and simulate biologically detailed neural models combined with deep learning elements, and apply deep learning training methods to optimize these models.
NengoDL is a software framework designed to combine the strengths of neuromorphic modelling and deep learning. NengoDL allows users to construct biologically detailed neural models, intermix those models with deep learning elements (such as convolutional networks), and then efficiently simulate those models in an easy-to-use, unified framework. In addition, NengoDL allows users to apply deep learning training methods to optimize the parameters of biological neural models. In this paper we present basic usage examples, benchmarking, and details on the key implementation elements of NengoDL. More details can be found at https://www.nengo.ai/nengo-dl .