NengoDL: Combining deep learning and neuromorphic modelling methods

TL;DR

NengoDL is a unified software framework that integrates neuromorphic modeling with deep learning, enabling construction, simulation, and training of biologically detailed neural models with deep learning techniques.

Contribution

It introduces NengoDL, a novel framework that combines neuromorphic modeling and deep learning, allowing for flexible model construction and training in a single environment.

Findings

Efficient simulation of combined neuromorphic and deep learning models

Successful application of deep learning training methods to biological neural models

Benchmarking demonstrating performance and flexibility of NengoDL

Abstract

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 .